Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4530 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.7243. Min Act: -0.1700
Data Index: 4648564 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.4431. Min Act: -0.1700
Data Index: 1989346 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.4118. Min Act: -0.1700
Data Index: 5996599 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.3806. Min Act: -0.1700
Data Index: 392560 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.2243. Min Act: -0.1700
Data Index: 1077837 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.1618. Min Act: -0.1700
Data Index: 6093752 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.1306. Min Act: -0.1700
Data Index: 3081645 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.0993. Min Act: -0.1700
Data Index: 7254634 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.0993. Min Act: -0.1700
Data Index: 684788 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.0993. Min Act: -0.1700
Data Index: 5581398 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7243. Min Range: -7.7243
Max Act: 7.0368. Min Act: -0.1700
Data Index: 4950655 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7243. Min Range: -7.7243
Max Act: 6.9431. Min Act: -0.1700
Data Index: 3227679 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7243. Min Range: -7.7243
Max Act: 6.9431. Min Act: -0.1700
Data Index: 3286121 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7243. Min Range: -7.7243
Max Act: 6.9431. Min Act: -0.1700
Data Index: 7348857 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7243. Min Range: -7.7243
Max Act: 6.9118. Min Act: -0.1700
Data Index: 3081111 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7243. Min Range: -7.7243
Max Act: 6.8806. Min Act: -0.1700
Data Index: 6688861 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7243. Min Range: -7.7243
Max Act: 6.8493. Min Act: -0.1700
Data Index: 2561493 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7243. Min Range: -7.7243
Max Act: 6.8181. Min Act: -0.1700
Data Index: 907062 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7243. Min Range: -7.7243
Max Act: 6.8181. Min Act: -0.1700
Data Index: 4884238 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7243. Min Range: -7.7243
Max Act: 6.8181. Min Act: -0.1700
Data Index: 4408868 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19