Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 925 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.2394. Min Act: -0.1700
Data Index: 6104720 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1769. Min Act: -0.1700
Data Index: 3877928 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.2082. Min Act: -0.1698
Data Index: 3701716 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.2082. Min Act: -0.1700
Data Index: 1178060 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.2082. Min Act: -0.1700
Data Index: 3590857 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.2082. Min Act: -0.1700
Data Index: 3382180 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1769. Min Act: -0.1697
Data Index: 314708 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.2082. Min Act: -0.1700
Data Index: 4670769 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.2394. Min Act: -0.1700
Data Index: 3054533 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.2082. Min Act: -0.1700
Data Index: 8445231 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1769. Min Act: -0.1700
Data Index: 1647521 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1769. Min Act: -0.1700
Data Index: 5505198 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1769. Min Act: -0.1700
Data Index: 725088 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1769. Min Act: -0.1697
Data Index: 7660398 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1769. Min Act: -0.1700
Data Index: 7358569 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1457. Min Act: -0.1693
Data Index: 2917580 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1457. Min Act: -0.1700
Data Index: 774624 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1457. Min Act: -0.1700
Data Index: 287801 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1457. Min Act: -0.1700
Data Index: 3001034 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2394. Min Range: -6.2394
Max Act: 6.1144. Min Act: -0.1700
Data Index: 8276975 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19