Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.1295. Min Act: -0.1700
Data Index: 974769 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.1295. Min Act: -0.1700
Data Index: 259906 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0358. Min Act: -0.1700
Data Index: 3573830 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9108. Min Act: -0.1700
Data Index: 685868 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9108. Min Act: -0.1700
Data Index: 7257185 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9108. Min Act: -0.1700
Data Index: 623801 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8483. Min Act: -0.1700
Data Index: 567719 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8170. Min Act: -0.1700
Data Index: 1660372 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8170. Min Act: -0.1700
Data Index: 3959821 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8170. Min Act: -0.1700
Data Index: 8151234 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8170. Min Act: -0.1700
Data Index: 8550212 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7858. Min Act: -0.1700
Data Index: 1787484 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7858. Min Act: -0.1700
Data Index: 6429505 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7858. Min Act: -0.1700
Data Index: 8442629 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7545. Min Act: -0.1699
Data Index: 667002 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7545. Min Act: -0.1700
Data Index: 1107201 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6920. Min Act: -0.1700
Data Index: 2956349 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7233. Min Act: -0.1700
Data Index: 4411453 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7233. Min Act: -0.1700
Data Index: 1033883 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7545. Min Act: -0.1700
Data Index: 6264269 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19