Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2069 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.9260. Min Act: -0.1700
Data Index: 7521953 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.7698. Min Act: -0.1700
Data Index: 8826417 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.6760. Min Act: -0.1700
Data Index: 7031379 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.5823. Min Act: -0.1700
Data Index: 5298621 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.5510. Min Act: -0.1700
Data Index: 2579282 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.5198. Min Act: -0.1700
Data Index: 8332583 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.5198. Min Act: -0.1700
Data Index: 6805300 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.4885. Min Act: -0.1700
Data Index: 3651704 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.4573. Min Act: -0.1700
Data Index: 6516515 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.4573. Min Act: -0.1700
Data Index: 2615437 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.4260. Min Act: -0.1700
Data Index: 7998771 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.3948. Min Act: -0.1700
Data Index: 5081364 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.4260. Min Act: -0.1700
Data Index: 7236546 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.4260. Min Act: -0.1700
Data Index: 5998884 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.3948. Min Act: -0.1700
Data Index: 2142703 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.3635. Min Act: -0.1700
Data Index: 4466401 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.3635. Min Act: -0.1700
Data Index: 7349848 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.3635. Min Act: -0.1700
Data Index: 3943511 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.3635. Min Act: -0.1700
Data Index: 6141456 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9260. Min Range: -6.9260
Max Act: 6.3323. Min Act: -0.1700
Data Index: 1495673 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19