Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 595 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.3323. Min Act: -0.1700
Data Index: 7634448 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.0823. Min Act: -0.1700
Data Index: 8049484 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.8635. Min Act: -0.1700
Data Index: 8150403 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.7385. Min Act: -0.1700
Data Index: 581054 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.7385. Min Act: -0.1700
Data Index: 2960144 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.6135. Min Act: -0.1700
Data Index: 8611309 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.5510. Min Act: -0.1700
Data Index: 4653314 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.5198. Min Act: -0.1700
Data Index: 5934643 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.5198. Min Act: -0.1700
Data Index: 2587462 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.4885. Min Act: -0.1700
Data Index: 3410891 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.4885. Min Act: -0.1700
Data Index: 2071596 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.4573. Min Act: -0.1700
Data Index: 5091611 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.4573. Min Act: -0.1700
Data Index: 1287693 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.4260. Min Act: -0.1700
Data Index: 3156375 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.3948. Min Act: -0.1700
Data Index: 6957633 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.3948. Min Act: -0.1700
Data Index: 5667345 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.3948. Min Act: -0.1700
Data Index: 5351813 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.3635. Min Act: -0.1700
Data Index: 6981901 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.3635. Min Act: -0.1700
Data Index: 3066763 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3323. Min Range: -7.3323
Max Act: 6.3635. Min Act: -0.1700
Data Index: 6485249 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19