Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4937 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.3448. Min Act: -0.1700
Data Index: 8577747 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.2823. Min Act: -0.1700
Data Index: 7561759 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.2510. Min Act: -0.1700
Data Index: 895827 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.1885. Min Act: -0.1700
Data Index: 3802037 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.1885. Min Act: -0.1700
Data Index: 7311706 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.1885. Min Act: -0.1700
Data Index: 3599143 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.1573. Min Act: -0.1700
Data Index: 5402006 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.1260. Min Act: -0.1700
Data Index: 7166125 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.1260. Min Act: -0.1700
Data Index: 4457983 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.1260. Min Act: -0.1700
Data Index: 4596931 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.1260. Min Act: -0.1700
Data Index: 1921881 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.0948. Min Act: -0.1700
Data Index: 6478764 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.0635. Min Act: -0.1700
Data Index: 6870889 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.0635. Min Act: -0.1700
Data Index: 8436407 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.0323. Min Act: -0.1700
Data Index: 6244726 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.0635. Min Act: -0.1700
Data Index: 7518279 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.0635. Min Act: -0.1700
Data Index: 3597423 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.0323. Min Act: -0.1700
Data Index: 288127 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.0323. Min Act: -0.1700
Data Index: 56513 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3448. Min Range: -5.3448
Max Act: 5.0323. Min Act: -0.1700
Data Index: 5828274 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19