Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.9379. Min Act: -0.1700
Data Index: 8185671 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.8129. Min Act: -0.1700
Data Index: 5496663 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.7817. Min Act: -0.1700
Data Index: 3844490 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.7504. Min Act: -0.1700
Data Index: 854280 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.7504. Min Act: -0.1700
Data Index: 1094028 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.6567. Min Act: -0.1700
Data Index: 2425277 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.6567. Min Act: -0.1700
Data Index: 2524925 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.6567. Min Act: -0.1700
Data Index: 5977786 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.6567. Min Act: -0.1700
Data Index: 719790 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5629. Min Act: -0.1700
Data Index: 6027784 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5942. Min Act: -0.1700
Data Index: 897838 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5942. Min Act: -0.1700
Data Index: 1086708 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5629. Min Act: -0.1700
Data Index: 1705706 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5629. Min Act: -0.1700
Data Index: 6202612 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5629. Min Act: -0.1700
Data Index: 418877 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5317. Min Act: -0.1700
Data Index: 5767739 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5004. Min Act: -0.1700
Data Index: 398350 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5004. Min Act: -0.1700
Data Index: 3388179 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5004. Min Act: -0.1700
Data Index: 7924356 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5004. Min Act: -0.1700
Data Index: 5465271 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19