Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 698 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.6356. Min Act: -0.1700
Data Index: 4536045 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.5551. Min Act: -0.1700
Data Index: 736355 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.5389. Min Act: -0.1700
Data Index: 4752706 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.5389. Min Act: -0.1700
Data Index: 2858275 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.5228. Min Act: -0.1700
Data Index: 5261429 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.5066. Min Act: -0.1700
Data Index: 1848554 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4904. Min Act: -0.1700
Data Index: 8243837 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4742. Min Act: -0.1700
Data Index: 723845 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4579. Min Act: -0.1700
Data Index: 2738120 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4742. Min Act: -0.1700
Data Index: 5593425 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4742. Min Act: -0.1700
Data Index: 3812812 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4579. Min Act: -0.1700
Data Index: 1055244 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4417. Min Act: -0.1700
Data Index: 4747145 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4417. Min Act: -0.1700
Data Index: 8658673 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4254. Min Act: -0.1700
Data Index: 3749613 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4417. Min Act: -0.1700
Data Index: 6265734 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4417. Min Act: -0.1700
Data Index: 3096299 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4417. Min Act: -0.1700
Data Index: 1757148 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4254. Min Act: -0.1700
Data Index: 4752707 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6356. Min Range: -2.6356
Max Act: 2.4091. Min Act: -0.1700
Data Index: 4936530 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19