Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3726 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0510. Min Range: -8.0510
Max Act: 8.0510. Min Act: -0.1700
Data Index: 4508058 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.9885. Min Act: -0.1700
Data Index: 1754451 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.6760. Min Act: -0.1700
Data Index: 1328283 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.5510. Min Act: -0.1700
Data Index: 3210455 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.5510. Min Act: -0.1700
Data Index: 7171972 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.5510. Min Act: -0.1700
Data Index: 1931544 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.5198. Min Act: -0.1700
Data Index: 2136607 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 3217895 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 4031037 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 3756974 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 1191170 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3948. Min Act: -0.1700
Data Index: 6632257 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 1221384 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3948. Min Act: -0.1700
Data Index: 6479315 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3635. Min Act: -0.1700
Data Index: 5527083 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3323. Min Act: -0.1700
Data Index: 725195 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3323. Min Act: -0.1700
Data Index: 8464925 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.2698. Min Act: -0.1700
Data Index: 1319807 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.2385. Min Act: -0.1700
Data Index: 2449733 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.2385. Min Act: -0.1700
Data Index: 6254692 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19