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

Dataset: Open Web Text

Neuron 57 in Layer 1

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: 2.0345. Min Range: -2.0345

Max Act: 2.0345. Min Act: -0.1699

Data Index: 4710043 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.0345. Min Range: -2.0345

Max Act: 2.0065. Min Act: -0.1700

Data Index: 3452795 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9981. Min Act: -0.1700

Data Index: 5569261 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9842. Min Act: -0.1699

Data Index: 762173 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9591. Min Act: -0.1700

Data Index: 5884832 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9524. Min Act: -0.1700

Data Index: 5165072 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9493. Min Act: -0.1700

Data Index: 320243 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9343. Min Act: -0.1700

Data Index: 6206551 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9485. Min Act: -0.1700

Data Index: 6045272 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9421. Min Act: -0.1700

Data Index: 1324931 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9355. Min Act: -0.1700

Data Index: 97671 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9287. Min Act: -0.1700

Data Index: 6952457 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9355. Min Act: -0.1700

Data Index: 6042457 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9324. Min Act: -0.1696

Data Index: 1317356 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9355. Min Act: -0.1700

Data Index: 1014939 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9256. Min Act: -0.1700

Data Index: 826360 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9355. Min Act: -0.1700

Data Index: 5903491 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9355. Min Act: -0.1700

Data Index: 1978287 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9355. Min Act: -0.1700

Data Index: 3423385 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9355. Min Act: -0.1700

Data Index: 5470331 (Open Web Text)

Max Activating Token Index: 3