< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 362 in Layer 2

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: 2.2284. Min Range: -2.2284

Max Act: 2.2284. Min Act: -0.1700

Data Index: 4210713 (Open Web Text)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1902. Min Act: -0.1700

Data Index: 906805 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1695. Min Act: -0.1700

Data Index: 5308920 (Open Web Text)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1554. Min Act: -0.1700

Data Index: 8339949 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1169. Min Act: -0.1700

Data Index: 4838152 (Open Web Text)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1203. Min Act: -0.1700

Data Index: 3872965 (Open Web Text)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1219. Min Act: -0.1700

Data Index: 8390368 (Open Web Text)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.0983. Min Act: -0.1700

Data Index: 5963002 (Open Web Text)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1143. Min Act: -0.1700

Data Index: 826391 (Open Web Text)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1067. Min Act: -0.1700

Data Index: 8457868 (Open Web Text)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1100. Min Act: -0.1700

Data Index: 1786201 (Open Web Text)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1103. Min Act: -0.1700

Data Index: 8375052 (Open Web Text)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1171. Min Act: -0.1700

Data Index: 2540187 (Open Web Text)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1170. Min Act: -0.1700

Data Index: 8266413 (Open Web Text)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.1034. Min Act: -0.1700

Data Index: 4563493 (Open Web Text)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.0939. Min Act: -0.1700

Data Index: 4080245 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.0911. Min Act: -0.1700

Data Index: 954555 (Open Web Text)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.0886. Min Act: -0.1700

Data Index: 7985978 (Open Web Text)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.0942. Min Act: -0.1700

Data Index: 7482411 (Open Web Text)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.2284. Min Range: -2.2284

Max Act: 2.0861. Min Act: -0.1700

Data Index: 5676845 (Open Web Text)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #19