Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4279. Min Range: -5.4279
Max Act: 5.4279. Min Act: -0.1700
Data Index: 6039213 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4279. Min Range: -5.4279
Max Act: 5.0529. Min Act: -0.1700
Data Index: 8412778 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4279. Min Range: -5.4279
Max Act: 5.0216. Min Act: -0.1700
Data Index: 3486112 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.9904. Min Act: -0.1700
Data Index: 2421689 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.9591. Min Act: -0.1700
Data Index: 8804268 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.9591. Min Act: -0.1700
Data Index: 7169173 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.8966. Min Act: -0.1700
Data Index: 7588198 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.8654. Min Act: -0.1700
Data Index: 3895551 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.7404. Min Act: -0.1700
Data Index: 5833517 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.7716. Min Act: -0.1700
Data Index: 3608898 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.7716. Min Act: -0.1700
Data Index: 8582609 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.7091. Min Act: -0.1700
Data Index: 877180 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.6779. Min Act: -0.1700
Data Index: 6841118 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.6779. Min Act: -0.1700
Data Index: 3840181 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.6779. Min Act: -0.1700
Data Index: 2813091 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.6779. Min Act: -0.1700
Data Index: 3633123 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.6779. Min Act: -0.1700
Data Index: 7326324 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.6466. Min Act: -0.1700
Data Index: 3255229 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.6466. Min Act: -0.1700
Data Index: 7378062 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4279. Min Range: -5.4279
Max Act: 4.6779. Min Act: -0.1700
Data Index: 2692623 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19