Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.9380. Min Act: -0.1700
Data Index: 5525721 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.9067. Min Act: -0.1700
Data Index: 3726734 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.8130. Min Act: -0.1700
Data Index: 6381758 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.8130. Min Act: -0.1700
Data Index: 3712958 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.7817. Min Act: -0.1700
Data Index: 3726728 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.7505. Min Act: -0.1700
Data Index: 1046260 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.7505. Min Act: -0.1700
Data Index: 3762579 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.7505. Min Act: -0.1700
Data Index: 3726733 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.7192. Min Act: -0.1700
Data Index: 5544316 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.7192. Min Act: -0.1700
Data Index: 6665353 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6880. Min Act: -0.1700
Data Index: 459472 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6880. Min Act: -0.1700
Data Index: 2663422 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6880. Min Act: -0.1700
Data Index: 3726738 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6255. Min Act: -0.1700
Data Index: 6381751 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6567. Min Act: -0.1700
Data Index: 904702 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6567. Min Act: -0.1700
Data Index: 6279878 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6567. Min Act: -0.1700
Data Index: 3726737 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6255. Min Act: -0.1700
Data Index: 2314271 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5942. Min Act: -0.1700
Data Index: 4006407 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5942. Min Act: -0.1700
Data Index: 519170 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19