< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 936 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.9349. Min Act: -0.1700

Data Index: 645536 (Open Web Text)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.9133. Min Act: -0.1700

Data Index: 1678215 (Open Web Text)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8987. Min Act: -0.1700

Data Index: 6163546 (Open Web Text)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.9018. Min Act: -0.1700

Data Index: 5576990 (Open Web Text)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8670. Min Act: -0.1700

Data Index: 139839 (Open Web Text)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8485. Min Act: -0.1700

Data Index: 8527384 (Open Web Text)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8554. Min Act: -0.1700

Data Index: 1815311 (Open Web Text)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8521. Min Act: -0.1700

Data Index: 7001478 (Open Web Text)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8425. Min Act: -0.1700

Data Index: 1771624 (Open Web Text)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8595. Min Act: -0.1700

Data Index: 8398260 (Open Web Text)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8233. Min Act: -0.1700

Data Index: 4191244 (Open Web Text)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8200. Min Act: -0.1700

Data Index: 141070 (Open Web Text)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8123. Min Act: -0.1700

Data Index: 5672101 (Open Web Text)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8269. Min Act: -0.1700

Data Index: 3680963 (Open Web Text)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8268. Min Act: -0.1700

Data Index: 2323845 (Open Web Text)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.7996. Min Act: -0.1700

Data Index: 1003978 (Open Web Text)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8243. Min Act: -0.1700

Data Index: 4045368 (Open Web Text)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.7961. Min Act: -0.1700

Data Index: 6655081 (Open Web Text)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8091. Min Act: -0.1700

Data Index: 6278950 (Open Web Text)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9349. Min Range: -2.9349

Max Act: 2.8031. Min Act: -0.1700

Data Index: 2112326 (Open Web Text)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #19