Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0280. Min Range: -6.0280
Max Act: 6.0280. Min Act: -0.1700
Data Index: 935659 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.9655. Min Act: -0.1700
Data Index: 7470889 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.9655. Min Act: -0.1700
Data Index: 7310308 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.9343. Min Act: -0.1700
Data Index: 3880239 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.9343. Min Act: -0.1700
Data Index: 4337089 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.7468. Min Act: -0.1700
Data Index: 2438002 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.7468. Min Act: -0.1700
Data Index: 1141472 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6843. Min Act: -0.1700
Data Index: 3059140 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.7155. Min Act: -0.1700
Data Index: 5536418 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6843. Min Act: -0.1700
Data Index: 5640540 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6843. Min Act: -0.1700
Data Index: 1401537 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6843. Min Act: -0.1700
Data Index: 6639048 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6843. Min Act: -0.1700
Data Index: 6773226 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6530. Min Act: -0.1700
Data Index: 7819372 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6530. Min Act: -0.1700
Data Index: 6517477 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6530. Min Act: -0.1700
Data Index: 756333 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6530. Min Act: -0.1700
Data Index: 867032 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6530. Min Act: -0.1700
Data Index: 1003415 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6530. Min Act: -0.1700
Data Index: 7838259 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0280. Min Range: -6.0280
Max Act: 5.6218. Min Act: -0.1700
Data Index: 5295553 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19