Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4130 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2039. Min Range: -5.2039
Max Act: 5.2039. Min Act: -0.1700
Data Index: 8788762 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2039. Min Range: -5.2039
Max Act: 5.1414. Min Act: -0.1700
Data Index: 5174303 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2039. Min Range: -5.2039
Max Act: 5.0476. Min Act: -0.1697
Data Index: 3757 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2039. Min Range: -5.2039
Max Act: 5.0476. Min Act: -0.1700
Data Index: 1072088 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9851. Min Act: -0.1700
Data Index: 4730452 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9226. Min Act: -0.1700
Data Index: 1055243 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9539. Min Act: -0.1700
Data Index: 7535948 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9539. Min Act: -0.1700
Data Index: 5396141 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9539. Min Act: -0.1700
Data Index: 654669 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9539. Min Act: -0.1700
Data Index: 4999079 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.8914. Min Act: -0.1700
Data Index: 5164794 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9226. Min Act: -0.1700
Data Index: 1927927 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9539. Min Act: -0.1700
Data Index: 4141745 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9226. Min Act: -0.1700
Data Index: 3710219 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9226. Min Act: -0.1700
Data Index: 7084121 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9226. Min Act: -0.1700
Data Index: 384997 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9226. Min Act: -0.1700
Data Index: 2635284 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9226. Min Act: -0.1700
Data Index: 2293373 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.9226. Min Act: -0.1700
Data Index: 7681522 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2039. Min Range: -5.2039
Max Act: 4.8914. Min Act: -0.1700
Data Index: 3523292 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19