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

Dataset: Open Web Text

Neuron 2529 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: 3.4864. Min Range: -3.4864

Max Act: 3.4864. Min Act: -0.1700

Data Index: 7442884 (Open Web Text)

Max Activating Token Index: 90

Text #1

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.4715. Min Act: -0.1700

Data Index: 5412171 (Open Web Text)

Max Activating Token Index: 928

Text #2

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3504. Min Act: -0.1700

Data Index: 2544792 (Open Web Text)

Max Activating Token Index: 475

Text #3

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.3728. Min Act: -0.1700

Data Index: 5694590 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.2934. Min Act: -0.1700

Data Index: 3002110 (Open Web Text)

Max Activating Token Index: 561

Text #5

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.2849. Min Act: -0.1700

Data Index: 5022917 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.2508. Min Act: -0.1700

Data Index: 826794 (Open Web Text)

Max Activating Token Index: 196

Text #7

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.2665. Min Act: -0.1700

Data Index: 3174634 (Open Web Text)

Max Activating Token Index: 376

Text #8

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.2170. Min Act: -0.1700

Data Index: 7176964 (Open Web Text)

Max Activating Token Index: 38

Text #9

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1799. Min Act: -0.1700

Data Index: 4700440 (Open Web Text)

Max Activating Token Index: 71

Text #10

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1695. Min Act: -0.1700

Data Index: 2975065 (Open Web Text)

Max Activating Token Index: 409

Text #11

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1670. Min Act: -0.1700

Data Index: 7865918 (Open Web Text)

Max Activating Token Index: 445

Text #12

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1547. Min Act: -0.1700

Data Index: 3957980 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1426. Min Act: -0.1700

Data Index: 5826508 (Open Web Text)

Max Activating Token Index: 134

Text #14

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1520. Min Act: -0.1700

Data Index: 7502598 (Open Web Text)

Max Activating Token Index: 46

Text #15

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1222. Min Act: -0.1700

Data Index: 3543095 (Open Web Text)

Max Activating Token Index: 252

Text #16

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1269. Min Act: -0.1700

Data Index: 1184220 (Open Web Text)

Max Activating Token Index: 224

Text #17

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1295. Min Act: -0.1700

Data Index: 1018237 (Open Web Text)

Max Activating Token Index: 80

Text #18

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1382. Min Act: -0.1700

Data Index: 3157866 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.1540. Min Act: -0.1700

Data Index: 2253335 (Open Web Text)

Max Activating Token Index: 894