Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3336 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1108. Min Range: -6.1108
Max Act: 6.1108. Min Act: -0.1700
Data Index: 8144102 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1108. Min Range: -6.1108
Max Act: 6.1108. Min Act: -0.1700
Data Index: 2759887 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1108. Min Range: -6.1108
Max Act: 6.0796. Min Act: -0.1700
Data Index: 1150883 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.9233. Min Act: -0.1700
Data Index: 2412595 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.8296. Min Act: -0.1700
Data Index: 3753393 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.7983. Min Act: -0.1700
Data Index: 7078139 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.7983. Min Act: -0.1700
Data Index: 1346575 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.7983. Min Act: -0.1700
Data Index: 1282961 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.8296. Min Act: -0.1700
Data Index: 985375 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.7671. Min Act: -0.1700
Data Index: 5173092 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.7358. Min Act: -0.1700
Data Index: 5044184 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.7358. Min Act: -0.1700
Data Index: 3031890 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.7358. Min Act: -0.1700
Data Index: 3131703 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.7046. Min Act: -0.1700
Data Index: 5110075 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.7046. Min Act: -0.1700
Data Index: 13376 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.6733. Min Act: -0.1700
Data Index: 3916763 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.6733. Min Act: -0.1700
Data Index: 601962 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.6421. Min Act: -0.1700
Data Index: 1837365 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.6421. Min Act: -0.1700
Data Index: 1384432 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1108. Min Range: -6.1108
Max Act: 5.6421. Min Act: -0.1700
Data Index: 3364114 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19