Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5031. Min Range: -7.5031
Max Act: 7.5031. Min Act: -0.1700
Data Index: 617014 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5031. Min Range: -7.5031
Max Act: 7.2843. Min Act: -0.1700
Data Index: 7879497 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5031. Min Range: -7.5031
Max Act: 7.1906. Min Act: -0.1700
Data Index: 8646403 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5031. Min Range: -7.5031
Max Act: 7.0968. Min Act: -0.1700
Data Index: 4957661 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5031. Min Range: -7.5031
Max Act: 7.0031. Min Act: -0.1700
Data Index: 7307240 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.9718. Min Act: -0.1700
Data Index: 5749438 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5031. Min Range: -7.5031
Max Act: 7.0031. Min Act: -0.1700
Data Index: 1354826 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.9718. Min Act: -0.1700
Data Index: 4251128 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.8781. Min Act: -0.1700
Data Index: 4160467 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.8781. Min Act: -0.1700
Data Index: 896140 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.8468. Min Act: -0.1700
Data Index: 3473543 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.8156. Min Act: -0.1700
Data Index: 3956701 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.7843. Min Act: -0.1700
Data Index: 7602977 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.7531. Min Act: -0.1700
Data Index: 7636754 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.7843. Min Act: -0.1700
Data Index: 4599316 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.7531. Min Act: -0.1700
Data Index: 2278192 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.7531. Min Act: -0.1700
Data Index: 3451282 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.7531. Min Act: -0.1700
Data Index: 2678948 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.7218. Min Act: -0.1700
Data Index: 5191477 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5031. Min Range: -7.5031
Max Act: 6.6906. Min Act: -0.1700
Data Index: 6883113 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19