Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 444 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.9677. Min Act: -0.1700
Data Index: 4117059 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.9677. Min Act: -0.1700
Data Index: 6401517 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.9677. Min Act: -0.1700
Data Index: 3015388 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.9052. Min Act: -0.1700
Data Index: 5937971 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.9364. Min Act: -0.1700
Data Index: 7282737 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.9364. Min Act: -0.1700
Data Index: 4138505 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.9364. Min Act: -0.1700
Data Index: 136855 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.9052. Min Act: -0.1700
Data Index: 8392317 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.8739. Min Act: -0.1700
Data Index: 1349029 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.9364. Min Act: -0.1700
Data Index: 3869649 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.8739. Min Act: -0.1700
Data Index: 7901547 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.8739. Min Act: -0.1700
Data Index: 7318871 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.9052. Min Act: -0.1700
Data Index: 3278505 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.8739. Min Act: -0.1700
Data Index: 7884622 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.8739. Min Act: -0.1700
Data Index: 349152 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.8427. Min Act: -0.1700
Data Index: 7141861 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.8427. Min Act: -0.1700
Data Index: 4573504 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.8427. Min Act: -0.1700
Data Index: 4518405 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.8427. Min Act: -0.1700
Data Index: 5201536 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9677. Min Range: -4.9677
Max Act: 4.8427. Min Act: -0.1700
Data Index: 5599255 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19