Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2546 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.8397. Min Act: -0.1700
Data Index: 887347 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.5897. Min Act: -0.1700
Data Index: 1326983 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.6209. Min Act: -0.1700
Data Index: 6626831 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.5584. Min Act: -0.1700
Data Index: 5373259 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.5272. Min Act: -0.1700
Data Index: 4998189 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.5272. Min Act: -0.1700
Data Index: 6765513 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.4959. Min Act: -0.1700
Data Index: 7182076 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.4959. Min Act: -0.1700
Data Index: 1985977 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.4647. Min Act: -0.1700
Data Index: 362007 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.4647. Min Act: -0.1700
Data Index: 3160472 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.4022. Min Act: -0.1700
Data Index: 5798529 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.4022. Min Act: -0.1700
Data Index: 3711134 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.3709. Min Act: -0.1700
Data Index: 3533120 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.3397. Min Act: -0.1700
Data Index: 4836623 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.3397. Min Act: -0.1700
Data Index: 5554015 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.3084. Min Act: -0.1700
Data Index: 6823187 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.3084. Min Act: -0.1700
Data Index: 4652488 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.2772. Min Act: -0.1700
Data Index: 6980455 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.2772. Min Act: -0.1700
Data Index: 1770853 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8397. Min Range: -6.8397
Max Act: 6.2772. Min Act: -0.1700
Data Index: 693682 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19