Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2626 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.5978. Min Act: -0.1700
Data Index: 3009770 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.5353. Min Act: -0.1700
Data Index: 1058838 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.5040. Min Act: -0.1700
Data Index: 5758350 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.4415. Min Act: -0.1700
Data Index: 2217406 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.4415. Min Act: -0.1700
Data Index: 7144881 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.4103. Min Act: -0.1700
Data Index: 2839220 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.4103. Min Act: -0.1700
Data Index: 6265195 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.3165. Min Act: -0.1700
Data Index: 36751 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.3165. Min Act: -0.1700
Data Index: 3590668 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.3165. Min Act: -0.1700
Data Index: 4580398 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.2853. Min Act: -0.1700
Data Index: 8481647 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.2853. Min Act: -0.1700
Data Index: 3689037 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.3165. Min Act: -0.1700
Data Index: 5964547 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.2853. Min Act: -0.1700
Data Index: 8173371 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.2540. Min Act: -0.1700
Data Index: 7345140 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.2540. Min Act: -0.1700
Data Index: 1591330 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.2228. Min Act: -0.1700
Data Index: 8255440 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.2228. Min Act: -0.1700
Data Index: 4245757 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.2228. Min Act: -0.1700
Data Index: 4080969 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5978. Min Range: -5.5978
Max Act: 5.1915. Min Act: -0.1700
Data Index: 274329 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19