Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 467 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2745. Min Range: -10.2745
Max Act: 10.2745. Min Act: -0.1700
Data Index: 8733680 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2745. Min Range: -10.2745
Max Act: 10.2120. Min Act: -0.1700
Data Index: 3228113 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2745. Min Range: -10.2745
Max Act: 10.0870. Min Act: -0.1700
Data Index: 5180942 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.8995. Min Act: -0.1700
Data Index: 4357282 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.8995. Min Act: -0.1700
Data Index: 5826095 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.7745. Min Act: -0.1700
Data Index: 2076115 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.7745. Min Act: -0.1700
Data Index: 273381 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.7120. Min Act: -0.1700
Data Index: 5362601 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.7120. Min Act: -0.1700
Data Index: 7636669 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.6495. Min Act: -0.1700
Data Index: 563792 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.6495. Min Act: -0.1700
Data Index: 836066 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.6495. Min Act: -0.1700
Data Index: 4960185 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.6495. Min Act: -0.1700
Data Index: 8646410 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.5870. Min Act: -0.1700
Data Index: 5754511 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.5870. Min Act: -0.1700
Data Index: 588651 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.5245. Min Act: -0.1700
Data Index: 1686158 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.5870. Min Act: -0.1700
Data Index: 5316192 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.5870. Min Act: -0.1700
Data Index: 6271060 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.5870. Min Act: -0.1700
Data Index: 4279207 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2745. Min Range: -10.2745
Max Act: 9.4620. Min Act: -0.1700
Data Index: 7692563 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19