Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1628. Min Act: -0.1700
Data Index: 2582123 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1628. Min Act: -0.1700
Data Index: 201628 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1003. Min Act: -0.1700
Data Index: 6663355 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1315. Min Act: -0.1700
Data Index: 3888502 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1315. Min Act: -0.1700
Data Index: 8653100 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1315. Min Act: -0.1700
Data Index: 7887876 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1315. Min Act: -0.1700
Data Index: 1221390 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1315. Min Act: -0.1700
Data Index: 610170 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1315. Min Act: -0.1700
Data Index: 1221395 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0690. Min Act: -0.1700
Data Index: 7863135 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1003. Min Act: -0.1700
Data Index: 8653101 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1003. Min Act: -0.1700
Data Index: 4084312 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0690. Min Act: -0.1700
Data Index: 4158826 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0690. Min Act: -0.1700
Data Index: 6408732 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 7828401 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0377. Min Act: -0.1700
Data Index: 1221394 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0377. Min Act: -0.1700
Data Index: 7708720 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 5097561 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0377. Min Act: -0.1700
Data Index: 3655656 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0377. Min Act: -0.1700
Data Index: 8828204 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19