Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5690 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2415. Min Range: -8.2415
Max Act: 8.2415. Min Act: -0.1700
Data Index: 219078 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2415. Min Range: -8.2415
Max Act: 7.9915. Min Act: -0.1700
Data Index: 4191691 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2415. Min Range: -8.2415
Max Act: 7.1790. Min Act: -0.1700
Data Index: 5522221 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2415. Min Range: -8.2415
Max Act: 7.1478. Min Act: -0.1700
Data Index: 7603483 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2415. Min Range: -8.2415
Max Act: 7.1165. Min Act: -0.1700
Data Index: 7043047 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2415. Min Range: -8.2415
Max Act: 7.0853. Min Act: -0.1700
Data Index: 5010264 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2415. Min Range: -8.2415
Max Act: 7.0228. Min Act: -0.1700
Data Index: 5773796 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2415. Min Range: -8.2415
Max Act: 7.0228. Min Act: -0.1700
Data Index: 8074282 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.9915. Min Act: -0.1700
Data Index: 3472223 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.9915. Min Act: -0.1700
Data Index: 2479041 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.9603. Min Act: -0.1700
Data Index: 6364545 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.9603. Min Act: -0.1700
Data Index: 6494234 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.9290. Min Act: -0.1700
Data Index: 6316662 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.9290. Min Act: -0.1700
Data Index: 2525838 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.9290. Min Act: -0.1700
Data Index: 5782601 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.8665. Min Act: -0.1700
Data Index: 5947200 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.8978. Min Act: -0.1700
Data Index: 8497973 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.8978. Min Act: -0.1700
Data Index: 4663876 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.8665. Min Act: -0.1700
Data Index: 7116907 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2415. Min Range: -8.2415
Max Act: 6.8978. Min Act: -0.1700
Data Index: 409686 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19