Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4863 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.1428. Min Range: -17.1428
Max Act: 17.1428. Min Act: -0.1700
Data Index: 6957088 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.8928. Min Act: -0.1700
Data Index: 1476538 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.1428. Min Range: -17.1428
Max Act: 17.0178. Min Act: -0.1700
Data Index: 2677081 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.8928. Min Act: -0.1700
Data Index: 3179329 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.8928. Min Act: -0.1700
Data Index: 11393 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.7678. Min Act: -0.1700
Data Index: 7025942 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.7678. Min Act: -0.1700
Data Index: 1924959 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.5178. Min Act: -0.1700
Data Index: 1924960 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.5178. Min Act: -0.1700
Data Index: 2920692 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.5178. Min Act: -0.1700
Data Index: 6161108 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.3928. Min Act: -0.1697
Data Index: 2153302 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.2678. Min Act: -0.1700
Data Index: 5732714 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.2678. Min Act: -0.1700
Data Index: 7078290 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.2053. Min Act: -0.1700
Data Index: 7988585 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.2053. Min Act: -0.1700
Data Index: 5994304 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.2053. Min Act: -0.1700
Data Index: 6684511 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.2053. Min Act: -0.1700
Data Index: 8578139 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.2678. Min Act: -0.1700
Data Index: 3846490 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.2053. Min Act: -0.1700
Data Index: 5314610 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.1428. Min Range: -17.1428
Max Act: 16.1428. Min Act: -0.1700
Data Index: 2847593 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19