Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5329. Min Range: -10.5329
Max Act: 10.5329. Min Act: -0.1700
Data Index: 8364242 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5329. Min Range: -10.5329
Max Act: 10.0329. Min Act: -0.1700
Data Index: 2431924 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5329. Min Range: -10.5329
Max Act: 10.0329. Min Act: -0.1700
Data Index: 945828 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.7829. Min Act: -0.1700
Data Index: 2521006 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.6579. Min Act: -0.1700
Data Index: 5512807 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.6579. Min Act: -0.1700
Data Index: 4607637 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.6579. Min Act: -0.1700
Data Index: 1457914 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.5329. Min Act: -0.1700
Data Index: 3867934 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.4704. Min Act: -0.1700
Data Index: 2832999 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.4704. Min Act: -0.1700
Data Index: 71369 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.4704. Min Act: -0.1700
Data Index: 4952792 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.4079. Min Act: -0.1700
Data Index: 4385383 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.4079. Min Act: -0.1700
Data Index: 708153 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.4079. Min Act: -0.1700
Data Index: 4757812 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.3454. Min Act: -0.1700
Data Index: 2374934 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.3454. Min Act: -0.1700
Data Index: 223460 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.3454. Min Act: -0.1700
Data Index: 3214599 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.4079. Min Act: -0.1700
Data Index: 5382125 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.3454. Min Act: -0.1700
Data Index: 326382 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5329. Min Range: -10.5329
Max Act: 9.3454. Min Act: -0.1700
Data Index: 5408206 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19