Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 565 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.9661. Min Act: -0.1700
Data Index: 7388655 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.9661. Min Act: -0.1700
Data Index: 6800769 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.9661. Min Act: -0.1700
Data Index: 4520482 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.9661. Min Act: -0.1700
Data Index: 6694968 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.9349. Min Act: -0.1700
Data Index: 3143059 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.9349. Min Act: -0.1700
Data Index: 6800770 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.9661. Min Act: -0.1700
Data Index: 5818788 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8880. Min Act: -0.1700
Data Index: 289456 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8567. Min Act: -0.1700
Data Index: 6800771 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8411. Min Act: -0.1700
Data Index: 3091284 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8723. Min Act: -0.1700
Data Index: 7654329 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8723. Min Act: -0.1700
Data Index: 6440710 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.9349. Min Act: -0.1700
Data Index: 2419296 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8880. Min Act: -0.1700
Data Index: 5399559 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8880. Min Act: -0.1700
Data Index: 8696854 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8723. Min Act: -0.1700
Data Index: 6280461 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8567. Min Act: -0.1700
Data Index: 3768352 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8411. Min Act: -0.1700
Data Index: 3713548 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8411. Min Act: -0.1700
Data Index: 7673371 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8411. Min Act: -0.1700
Data Index: 5283708 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19