Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4399 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2649. Min Range: -6.2649
Max Act: 6.2649. Min Act: -0.1700
Data Index: 5636308 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2649. Min Range: -6.2649
Max Act: 6.1399. Min Act: -0.1700
Data Index: 615266 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2649. Min Range: -6.2649
Max Act: 6.1086. Min Act: -0.1700
Data Index: 7219218 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2649. Min Range: -6.2649
Max Act: 6.0774. Min Act: -0.1700
Data Index: 7052504 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2649. Min Range: -6.2649
Max Act: 6.0461. Min Act: -0.1700
Data Index: 4984995 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2649. Min Range: -6.2649
Max Act: 6.0149. Min Act: -0.1700
Data Index: 5767490 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2649. Min Range: -6.2649
Max Act: 6.0149. Min Act: -0.1700
Data Index: 3354265 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2649. Min Range: -6.2649
Max Act: 6.0149. Min Act: -0.1700
Data Index: 6201366 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.9836. Min Act: -0.1700
Data Index: 244428 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.9836. Min Act: -0.1700
Data Index: 6285986 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.9211. Min Act: -0.1700
Data Index: 899032 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.9524. Min Act: -0.1700
Data Index: 5700031 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.8899. Min Act: -0.1700
Data Index: 5797401 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.8899. Min Act: -0.1700
Data Index: 3089530 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.8586. Min Act: -0.1700
Data Index: 8503164 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.8586. Min Act: -0.1700
Data Index: 138888 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.8586. Min Act: -0.1700
Data Index: 2986212 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.8274. Min Act: -0.1700
Data Index: 6473136 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.7961. Min Act: -0.1700
Data Index: 1478150 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2649. Min Range: -6.2649
Max Act: 5.7961. Min Act: -0.1700
Data Index: 1059024 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19