Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4708 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.6740. Min Act: -0.1700
Data Index: 6556814 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.6115. Min Act: -0.1700
Data Index: 4444439 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.5803. Min Act: -0.1700
Data Index: 4199491 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.5803. Min Act: -0.1700
Data Index: 4132691 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.5490. Min Act: -0.1700
Data Index: 3361897 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.5178. Min Act: -0.1700
Data Index: 8812528 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.5178. Min Act: -0.1700
Data Index: 3198733 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.5178. Min Act: -0.1700
Data Index: 110739 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.5178. Min Act: -0.1700
Data Index: 4141351 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.5178. Min Act: -0.1700
Data Index: 6061457 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.4553. Min Act: -0.1700
Data Index: 7526117 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.4865. Min Act: -0.1700
Data Index: 2971548 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.4553. Min Act: -0.1700
Data Index: 7644013 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.4553. Min Act: -0.1700
Data Index: 47928 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.4553. Min Act: -0.1700
Data Index: 7816797 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.4865. Min Act: -0.1700
Data Index: 1690555 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.4240. Min Act: -0.1700
Data Index: 6043923 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.4240. Min Act: -0.1700
Data Index: 3296989 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.4553. Min Act: -0.1700
Data Index: 2617780 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6740. Min Range: -5.6740
Max Act: 5.3928. Min Act: -0.1700
Data Index: 1363462 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19