Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5694 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0439. Min Range: -6.0439
Max Act: 6.0439. Min Act: -0.1700
Data Index: 4931037 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0439. Min Range: -6.0439
Max Act: 6.0126. Min Act: -0.1700
Data Index: 6153498 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.8876. Min Act: -0.1700
Data Index: 4926708 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.7626. Min Act: -0.1700
Data Index: 5565176 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.7001. Min Act: -0.1700
Data Index: 4117158 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.6689. Min Act: -0.1700
Data Index: 6282204 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.6376. Min Act: -0.1700
Data Index: 2990915 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.6689. Min Act: -0.1700
Data Index: 3796458 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.6064. Min Act: -0.1700
Data Index: 961669 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.6064. Min Act: -0.1700
Data Index: 8619388 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.5439. Min Act: -0.1700
Data Index: 2520447 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.5751. Min Act: -0.1700
Data Index: 6054357 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.5126. Min Act: -0.1700
Data Index: 7285720 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.5439. Min Act: -0.1700
Data Index: 4975750 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.4814. Min Act: -0.1700
Data Index: 6353732 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.4189. Min Act: -0.1700
Data Index: 5318192 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.4501. Min Act: -0.1700
Data Index: 3800321 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.4189. Min Act: -0.1700
Data Index: 7474801 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.4189. Min Act: -0.1700
Data Index: 5802417 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0439. Min Range: -6.0439
Max Act: 5.3876. Min Act: -0.1700
Data Index: 1431424 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19