Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.5973. Min Act: -0.1700
Data Index: 687244 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.5661. Min Act: -0.1700
Data Index: 233033 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.5036. Min Act: -0.1700
Data Index: 6390060 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.5348. Min Act: -0.1700
Data Index: 6721551 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.3473. Min Act: -0.1700
Data Index: 582554 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.2223. Min Act: -0.1700
Data Index: 4380487 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.2223. Min Act: -0.1700
Data Index: 1214449 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.1911. Min Act: -0.1700
Data Index: 7281020 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.2223. Min Act: -0.1700
Data Index: 4689562 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.1598. Min Act: -0.1700
Data Index: 5643941 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.1598. Min Act: -0.1700
Data Index: 7769095 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.1286. Min Act: -0.1700
Data Index: 1575300 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.1286. Min Act: -0.1700
Data Index: 5806611 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.0661. Min Act: -0.1700
Data Index: 3036530 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.0661. Min Act: -0.1700
Data Index: 6094329 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.0348. Min Act: -0.1700
Data Index: 8253320 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.0036. Min Act: -0.1700
Data Index: 5529038 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.0036. Min Act: -0.1700
Data Index: 7949724 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5973. Min Range: -6.5973
Max Act: 6.0036. Min Act: -0.1700
Data Index: 7366516 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5973. Min Range: -6.5973
Max Act: 5.9723. Min Act: -0.1700
Data Index: 3891688 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19