Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7621. Min Act: -0.1700
Data Index: 3920491 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7464. Min Act: -0.1700
Data Index: 3550005 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7464. Min Act: -0.1700
Data Index: 1801256 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6838. Min Act: -0.1700
Data Index: 7567613 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6838. Min Act: -0.1700
Data Index: 7954087 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6526. Min Act: -0.1700
Data Index: 4439649 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.5743. Min Act: -0.1700
Data Index: 7954081 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.5900. Min Act: -0.1700
Data Index: 7355783 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.5430. Min Act: -0.1700
Data Index: 7746139 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.5430. Min Act: -0.1700
Data Index: 7187977 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4960. Min Act: -0.1700
Data Index: 891534 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4333. Min Act: -0.1700
Data Index: 5599648 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4333. Min Act: -0.1700
Data Index: 6144904 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4333. Min Act: -0.1700
Data Index: 3017885 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4333. Min Act: -0.1700
Data Index: 2357221 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4333. Min Act: -0.1700
Data Index: 7954088 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4177. Min Act: -0.1700
Data Index: 8212382 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4177. Min Act: -0.1700
Data Index: 7968392 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4177. Min Act: -0.1700
Data Index: 5793195 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4177. Min Act: -0.1700
Data Index: 796219 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19