Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2480 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.7983. Min Act: -0.1700
Data Index: 3821500 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.5795. Min Act: -0.1700
Data Index: 3518191 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.5170. Min Act: -0.1700
Data Index: 6421958 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.3295. Min Act: -0.1700
Data Index: 2323410 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2983. Min Act: -0.1700
Data Index: 2259503 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.3295. Min Act: -0.1700
Data Index: 6045375 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2670. Min Act: -0.1700
Data Index: 503794 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2670. Min Act: -0.1700
Data Index: 6906798 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2358. Min Act: -0.1700
Data Index: 6143987 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2358. Min Act: -0.1700
Data Index: 5074570 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2358. Min Act: -0.1700
Data Index: 7786109 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2045. Min Act: -0.1700
Data Index: 3821497 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1733. Min Act: -0.1700
Data Index: 2369932 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1733. Min Act: -0.1700
Data Index: 5072638 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1420. Min Act: -0.1700
Data Index: 105845 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1420. Min Act: -0.1700
Data Index: 3830032 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1420. Min Act: -0.1700
Data Index: 1246659 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1420. Min Act: -0.1700
Data Index: 7490111 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1420. Min Act: -0.1700
Data Index: 5269852 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1420. Min Act: -0.1700
Data Index: 6527647 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19