Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3227. Min Range: -5.3227
Max Act: 5.3227. Min Act: -0.1700
Data Index: 7447817 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3227. Min Range: -5.3227
Max Act: 5.0727. Min Act: -0.1700
Data Index: 6544463 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3227. Min Range: -5.3227
Max Act: 5.0414. Min Act: -0.1700
Data Index: 2578840 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3227. Min Range: -5.3227
Max Act: 5.0102. Min Act: -0.1700
Data Index: 7660851 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3227. Min Range: -5.3227
Max Act: 5.0102. Min Act: -0.1700
Data Index: 5026197 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.9789. Min Act: -0.1700
Data Index: 4555535 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.9789. Min Act: -0.1700
Data Index: 2507775 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.9477. Min Act: -0.1700
Data Index: 3090310 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.9477. Min Act: -0.1700
Data Index: 3917516 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.9477. Min Act: -0.1700
Data Index: 5441607 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.9477. Min Act: -0.1700
Data Index: 6334130 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.9477. Min Act: -0.1700
Data Index: 6365479 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.9164. Min Act: -0.1700
Data Index: 8057628 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.9477. Min Act: -0.1700
Data Index: 5344479 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.8852. Min Act: -0.1700
Data Index: 2232340 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.8852. Min Act: -0.1700
Data Index: 4550440 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.8852. Min Act: -0.1700
Data Index: 4741706 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.8227. Min Act: -0.1700
Data Index: 3124190 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.8539. Min Act: -0.1700
Data Index: 2967573 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3227. Min Range: -5.3227
Max Act: 4.8852. Min Act: -0.1700
Data Index: 3001835 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19