Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1190 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5420. Min Range: -7.5420
Max Act: 7.5420. Min Act: -0.1700
Data Index: 7340503 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5420. Min Range: -7.5420
Max Act: 7.0732. Min Act: -0.1700
Data Index: 1645832 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5420. Min Range: -7.5420
Max Act: 7.1045. Min Act: -0.1700
Data Index: 4058945 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5420. Min Range: -7.5420
Max Act: 7.0732. Min Act: -0.1700
Data Index: 464600 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5420. Min Range: -7.5420
Max Act: 7.0107. Min Act: -0.1700
Data Index: 3394098 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.9482. Min Act: -0.1700
Data Index: 3127782 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.8857. Min Act: -0.1700
Data Index: 4329347 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.8857. Min Act: -0.1700
Data Index: 6118818 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.8857. Min Act: -0.1700
Data Index: 6878830 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.8857. Min Act: -0.1700
Data Index: 610055 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.8857. Min Act: -0.1700
Data Index: 6630169 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.8545. Min Act: -0.1700
Data Index: 7368096 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.8232. Min Act: -0.1700
Data Index: 1627179 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.7920. Min Act: -0.1700
Data Index: 3715335 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.7920. Min Act: -0.1700
Data Index: 3559969 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.7607. Min Act: -0.1700
Data Index: 2083726 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.7920. Min Act: -0.1700
Data Index: 6165772 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.7607. Min Act: -0.1700
Data Index: 4681542 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.7295. Min Act: -0.1700
Data Index: 1389777 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5420. Min Range: -7.5420
Max Act: 6.7295. Min Act: -0.1700
Data Index: 300631 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19