Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5823 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3517. Min Range: -7.3517
Max Act: 7.3517. Min Act: -0.1700
Data Index: 6266318 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3517. Min Range: -7.3517
Max Act: 7.1017. Min Act: -0.1700
Data Index: 8530928 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.9142. Min Act: -0.1700
Data Index: 2270809 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.9142. Min Act: -0.1700
Data Index: 964728 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.8517. Min Act: -0.1700
Data Index: 5561366 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.8517. Min Act: -0.1700
Data Index: 6602483 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.7892. Min Act: -0.1700
Data Index: 6151691 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.7892. Min Act: -0.1700
Data Index: 7396204 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.7580. Min Act: -0.1700
Data Index: 2908171 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.7580. Min Act: -0.1700
Data Index: 4192730 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.6955. Min Act: -0.1700
Data Index: 167615 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.6955. Min Act: -0.1700
Data Index: 2229117 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.6955. Min Act: -0.1700
Data Index: 4966128 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.6955. Min Act: -0.1700
Data Index: 1357857 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.6955. Min Act: -0.1700
Data Index: 4127088 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.6330. Min Act: -0.1700
Data Index: 5341728 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.6642. Min Act: -0.1700
Data Index: 5427145 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.6330. Min Act: -0.1700
Data Index: 1866164 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.6330. Min Act: -0.1700
Data Index: 707375 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3517. Min Range: -7.3517
Max Act: 6.6017. Min Act: -0.1700
Data Index: 5032728 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19