Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.8996. Min Act: -0.1700
Data Index: 2305921 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.7746. Min Act: -0.1700
Data Index: 2547409 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.7434. Min Act: -0.1700
Data Index: 238014 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.7121. Min Act: -0.1700
Data Index: 4735588 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.6809. Min Act: -0.1700
Data Index: 7006378 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.6184. Min Act: -0.1700
Data Index: 5433724 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.6184. Min Act: -0.1700
Data Index: 8792374 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.5559. Min Act: -0.1700
Data Index: 2050965 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.5559. Min Act: -0.1700
Data Index: 398239 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.5246. Min Act: -0.1700
Data Index: 582608 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.5559. Min Act: -0.1700
Data Index: 5212464 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.5246. Min Act: -0.1700
Data Index: 136623 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.5246. Min Act: -0.1700
Data Index: 974345 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.5246. Min Act: -0.1700
Data Index: 8328999 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.5246. Min Act: -0.1700
Data Index: 3424504 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.4934. Min Act: -0.1700
Data Index: 1019861 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.4934. Min Act: -0.1700
Data Index: 6430888 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.4934. Min Act: -0.1700
Data Index: 5445146 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.4621. Min Act: -0.1700
Data Index: 7080850 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8996. Min Range: -7.8996
Max Act: 7.4621. Min Act: -0.1700
Data Index: 5649699 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19