Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.5346. Min Act: -0.1700
Data Index: 7753052 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.4721. Min Act: -0.1700
Data Index: 8263381 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.3471. Min Act: -0.1700
Data Index: 4212010 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.3471. Min Act: -0.1700
Data Index: 6496024 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.2221. Min Act: -0.1700
Data Index: 1218036 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.2221. Min Act: -0.1700
Data Index: 3549504 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.1596. Min Act: -0.1700
Data Index: 5815867 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.1596. Min Act: -0.1700
Data Index: 6947687 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.1596. Min Act: -0.1700
Data Index: 7610133 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.1284. Min Act: -0.1700
Data Index: 5401391 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.0971. Min Act: -0.1700
Data Index: 2946932 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.0659. Min Act: -0.1700
Data Index: 7054402 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.0346. Min Act: -0.1700
Data Index: 2258980 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.0346. Min Act: -0.1700
Data Index: 6004529 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.0346. Min Act: -0.1700
Data Index: 3540902 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5346. Min Range: -6.5346
Max Act: 5.9721. Min Act: -0.1700
Data Index: 6821732 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.0034. Min Act: -0.1700
Data Index: 6631779 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5346. Min Range: -6.5346
Max Act: 5.9721. Min Act: -0.1700
Data Index: 5124030 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5346. Min Range: -6.5346
Max Act: 5.9721. Min Act: -0.1700
Data Index: 1328076 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.0034. Min Act: -0.1700
Data Index: 117615 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19