Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5117 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.7723. Min Act: -0.1700
Data Index: 8491113 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.7410. Min Act: -0.1700
Data Index: 7621850 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.7410. Min Act: -0.1700
Data Index: 3718302 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.7098. Min Act: -0.1700
Data Index: 4284521 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.6785. Min Act: -0.1700
Data Index: 6726950 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.6473. Min Act: -0.1700
Data Index: 7377769 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.6473. Min Act: -0.1700
Data Index: 191049 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.6473. Min Act: -0.1700
Data Index: 5437241 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.5848. Min Act: -0.1700
Data Index: 2224815 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.5848. Min Act: -0.1700
Data Index: 2817529 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.5848. Min Act: -0.1700
Data Index: 8479469 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.5848. Min Act: -0.1700
Data Index: 962270 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.5223. Min Act: -0.1700
Data Index: 1394039 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.5223. Min Act: -0.1700
Data Index: 8460691 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.4910. Min Act: -0.1700
Data Index: 1128690 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.5223. Min Act: -0.1700
Data Index: 4012794 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.4910. Min Act: -0.1700
Data Index: 8479864 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.4285. Min Act: -0.1700
Data Index: 5285200 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.4285. Min Act: -0.1700
Data Index: 7411700 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7723. Min Range: -4.7723
Max Act: 4.3973. Min Act: -0.1700
Data Index: 6726948 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19