Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3082. Min Range: -8.3082
Max Act: 8.3082. Min Act: -0.1700
Data Index: 5084020 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3082. Min Range: -8.3082
Max Act: 8.1832. Min Act: -0.1700
Data Index: 83605 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3082. Min Range: -8.3082
Max Act: 8.0582. Min Act: -0.1700
Data Index: 2574494 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3082. Min Range: -8.3082
Max Act: 8.0582. Min Act: -0.1700
Data Index: 6359667 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.9957. Min Act: -0.1700
Data Index: 7922931 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.9645. Min Act: -0.1700
Data Index: 8036603 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.8395. Min Act: -0.1700
Data Index: 1610898 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.8082. Min Act: -0.1700
Data Index: 7422417 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.8082. Min Act: -0.1700
Data Index: 561733 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.8082. Min Act: -0.1700
Data Index: 5307313 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.7457. Min Act: -0.1700
Data Index: 6215979 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.7457. Min Act: -0.1700
Data Index: 932589 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.7145. Min Act: -0.1700
Data Index: 7845726 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.6832. Min Act: -0.1700
Data Index: 6237554 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.6832. Min Act: -0.1700
Data Index: 4083674 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.6832. Min Act: -0.1700
Data Index: 6569398 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.6832. Min Act: -0.1700
Data Index: 5980345 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.6520. Min Act: -0.1700
Data Index: 4402891 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.6207. Min Act: -0.1700
Data Index: 374087 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3082. Min Range: -8.3082
Max Act: 7.5895. Min Act: -0.1700
Data Index: 6844663 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19