Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3806 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.8973. Min Act: -0.1700
Data Index: 5981439 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.8348. Min Act: -0.1700
Data Index: 7936853 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.7098. Min Act: -0.1700
Data Index: 3027068 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.5223. Min Act: -0.1700
Data Index: 3610221 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.4911. Min Act: -0.1700
Data Index: 212531 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.4911. Min Act: -0.1700
Data Index: 967999 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.4598. Min Act: -0.1700
Data Index: 2930593 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.3661. Min Act: -0.1700
Data Index: 5350757 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.3661. Min Act: -0.1700
Data Index: 7247666 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.3348. Min Act: -0.1700
Data Index: 5291588 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.3348. Min Act: -0.1700
Data Index: 625410 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.3036. Min Act: -0.1700
Data Index: 6804331 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.3036. Min Act: -0.1700
Data Index: 599722 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.2411. Min Act: -0.1700
Data Index: 3856818 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.2723. Min Act: -0.1700
Data Index: 5956888 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.2723. Min Act: -0.1700
Data Index: 4555423 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.2723. Min Act: -0.1700
Data Index: 5619117 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.2723. Min Act: -0.1700
Data Index: 6550738 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.2098. Min Act: -0.1700
Data Index: 5061623 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8973. Min Range: -7.8973
Max Act: 7.2411. Min Act: -0.1700
Data Index: 877718 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19