Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5530 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.4038. Min Act: -0.1700
Data Index: 4398709 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.3724. Min Act: -0.1700
Data Index: 3131776 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.3567. Min Act: -0.1700
Data Index: 708600 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.3567. Min Act: -0.1700
Data Index: 7966961 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.3567. Min Act: -0.1700
Data Index: 7842853 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.3096. Min Act: -0.1700
Data Index: 4610196 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2939. Min Act: -0.1700
Data Index: 7928121 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.3096. Min Act: -0.1700
Data Index: 2579577 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2782. Min Act: -0.1700
Data Index: 3190482 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2782. Min Act: -0.1700
Data Index: 4760609 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2625. Min Act: -0.1700
Data Index: 6162778 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2782. Min Act: -0.1700
Data Index: 4060470 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2782. Min Act: -0.1700
Data Index: 1685752 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2468. Min Act: -0.1700
Data Index: 3265507 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2311. Min Act: -0.1700
Data Index: 7527369 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2311. Min Act: -0.1700
Data Index: 7418595 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2154. Min Act: -0.1700
Data Index: 4398704 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2154. Min Act: -0.1700
Data Index: 2671379 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2154. Min Act: -0.1700
Data Index: 8779924 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4038. Min Range: -3.4038
Max Act: 3.2311. Min Act: -0.1700
Data Index: 2618825 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19