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

Dataset: Open Web Text

Neuron 1209 in Layer 3

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: 4.4156. Min Range: -4.4156

Max Act: 4.4156. Min Act: -0.1700

Data Index: 8354327 (Open Web Text)

Max Activating Token Index: 472

Text #1

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.4025. Min Act: -0.1700

Data Index: 235505 (Open Web Text)

Max Activating Token Index: 639

Text #2

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.3646. Min Act: -0.1700

Data Index: 3790171 (Open Web Text)

Max Activating Token Index: 734

Text #3

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.3062. Min Act: -0.1700

Data Index: 5627866 (Open Web Text)

Max Activating Token Index: 374

Text #4

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.2989. Min Act: -0.1700

Data Index: 6859018 (Open Web Text)

Max Activating Token Index: 368

Text #5

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.2070. Min Act: -0.1700

Data Index: 7516208 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.2041. Min Act: -0.1700

Data Index: 780368 (Open Web Text)

Max Activating Token Index: 429

Text #7

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.2516. Min Act: -0.1700

Data Index: 3622861 (Open Web Text)

Max Activating Token Index: 846

Text #8

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1994. Min Act: -0.1700

Data Index: 1643321 (Open Web Text)

Max Activating Token Index: 46

Text #9

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.2590. Min Act: -0.1700

Data Index: 3106974 (Open Web Text)

Max Activating Token Index: 627

Text #10

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1837. Min Act: -0.1700

Data Index: 6198754 (Open Web Text)

Max Activating Token Index: 441

Text #11

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1770. Min Act: -0.1700

Data Index: 1643320 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1694. Min Act: -0.1700

Data Index: 1643318 (Open Web Text)

Max Activating Token Index: 910

Text #13

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1608. Min Act: -0.1700

Data Index: 4343939 (Open Web Text)

Max Activating Token Index: 932

Text #14

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1369. Min Act: -0.1700

Data Index: 6613737 (Open Web Text)

Max Activating Token Index: 708

Text #15

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1389. Min Act: -0.1700

Data Index: 6241799 (Open Web Text)

Max Activating Token Index: 687

Text #16

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1100. Min Act: -0.1700

Data Index: 5434914 (Open Web Text)

Max Activating Token Index: 933

Text #17

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1220. Min Act: -0.1700

Data Index: 6452892 (Open Web Text)

Max Activating Token Index: 488

Text #18

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1041. Min Act: -0.1700

Data Index: 5520760 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 4.4156. Min Range: -4.4156

Max Act: 4.1214. Min Act: -0.1700

Data Index: 3545019 (Open Web Text)

Max Activating Token Index: 10