Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3902 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1942. Min Range: -7.1942
Max Act: 7.1942. Min Act: -0.1700
Data Index: 7415535 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1942. Min Range: -7.1942
Max Act: 7.0692. Min Act: -0.1700
Data Index: 4076908 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.9130. Min Act: -0.1700
Data Index: 656158 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.9130. Min Act: -0.1700
Data Index: 3781961 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.8505. Min Act: -0.1700
Data Index: 3160881 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.8192. Min Act: -0.1700
Data Index: 7048144 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.7880. Min Act: -0.1700
Data Index: 4702405 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.7567. Min Act: -0.1700
Data Index: 3588886 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.7567. Min Act: -0.1700
Data Index: 3826603 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.7255. Min Act: -0.1700
Data Index: 4801896 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.6317. Min Act: -0.1700
Data Index: 3323402 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.6317. Min Act: -0.1700
Data Index: 1159881 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.6317. Min Act: -0.1700
Data Index: 3162307 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.5692. Min Act: -0.1700
Data Index: 5658004 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.6005. Min Act: -0.1700
Data Index: 855378 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.6005. Min Act: -0.1700
Data Index: 1907971 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.5692. Min Act: -0.1700
Data Index: 3298979 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.5692. Min Act: -0.1700
Data Index: 1133022 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.5692. Min Act: -0.1700
Data Index: 2092577 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1942. Min Range: -7.1942
Max Act: 6.5067. Min Act: -0.1700
Data Index: 6393842 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19