Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5100 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.8349. Min Act: -0.1700
Data Index: 1249513 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.8036. Min Act: -0.1700
Data Index: 2933383 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.7724. Min Act: -0.1700
Data Index: 5152058 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.7724. Min Act: -0.1700
Data Index: 4956429 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.7099. Min Act: -0.1700
Data Index: 8238478 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.7411. Min Act: -0.1700
Data Index: 6417148 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.7411. Min Act: -0.1700
Data Index: 3170861 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.7099. Min Act: -0.1700
Data Index: 2782540 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 7937213 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 2213475 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 3041087 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6474. Min Act: -0.1700
Data Index: 1027860 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6161. Min Act: -0.1700
Data Index: 3464919 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6161. Min Act: -0.1700
Data Index: 389063 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6161. Min Act: -0.1700
Data Index: 4827504 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.5849. Min Act: -0.1700
Data Index: 2207335 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.5849. Min Act: -0.1700
Data Index: 3625216 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.5849. Min Act: -0.1700
Data Index: 4908132 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6161. Min Act: -0.1700
Data Index: 2563436 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.5849. Min Act: -0.1700
Data Index: 766589 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19