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

Dataset: Open Web Text

Neuron 525 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: 2.0151. Min Range: -2.0151

Max Act: 2.0129. Min Act: -0.1700

Data Index: 5329597 (Open Web Text)

Max Activating Token Index: 256

Text #1

Max Range: 2.0151. Min Range: -2.0151

Max Act: 2.0106. Min Act: -0.1700

Data Index: 7214868 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 2.0151. Min Range: -2.0151

Max Act: 2.0151. Min Act: -0.1700

Data Index: 6915393 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 2.0151. Min Range: -2.0151

Max Act: 2.0018. Min Act: -0.1700

Data Index: 2738507 (Open Web Text)

Max Activating Token Index: 587

Text #4

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9940. Min Act: -0.1700

Data Index: 7861393 (Open Web Text)

Max Activating Token Index: 738

Text #5

Max Range: 2.0151. Min Range: -2.0151

Max Act: 2.0120. Min Act: -0.1700

Data Index: 6384829 (Open Web Text)

Max Activating Token Index: 272

Text #6

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9981. Min Act: -0.1700

Data Index: 8221365 (Open Web Text)

Max Activating Token Index: 114

Text #7

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9856. Min Act: -0.1700

Data Index: 7224749 (Open Web Text)

Max Activating Token Index: 283

Text #8

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9687. Min Act: -0.1700

Data Index: 2899203 (Open Web Text)

Max Activating Token Index: 629

Text #9

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9754. Min Act: -0.1700

Data Index: 5000911 (Open Web Text)

Max Activating Token Index: 750

Text #10

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9533. Min Act: -0.1700

Data Index: 3444925 (Open Web Text)

Max Activating Token Index: 30

Text #11

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9526. Min Act: -0.1700

Data Index: 5136522 (Open Web Text)

Max Activating Token Index: 186

Text #12

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9595. Min Act: -0.1700

Data Index: 6762761 (Open Web Text)

Max Activating Token Index: 33

Text #13

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9348. Min Act: -0.1700

Data Index: 859682 (Open Web Text)

Max Activating Token Index: 159

Text #14

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9471. Min Act: -0.1700

Data Index: 8091810 (Open Web Text)

Max Activating Token Index: 52

Text #15

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9357. Min Act: -0.1700

Data Index: 5276576 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9308. Min Act: -0.1700

Data Index: 8542945 (Open Web Text)

Max Activating Token Index: 63

Text #17

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9292. Min Act: -0.1700

Data Index: 374748 (Open Web Text)

Max Activating Token Index: 578

Text #18

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9267. Min Act: -0.1699

Data Index: 3364087 (Open Web Text)

Max Activating Token Index: 963

Text #19

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.9230. Min Act: -0.1700

Data Index: 6537254 (Open Web Text)

Max Activating Token Index: 280