Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.6197. Min Act: -0.1700
Data Index: 1080058 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5572. Min Act: -0.1700
Data Index: 5848899 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4634. Min Act: -0.1700
Data Index: 1059057 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4634. Min Act: -0.1700
Data Index: 570550 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4634. Min Act: -0.1700
Data Index: 1924350 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 2478562 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4009. Min Act: -0.1700
Data Index: 1248121 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 7100293 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 5758119 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3384. Min Act: -0.1700
Data Index: 6456904 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 6925601 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3384. Min Act: -0.1700
Data Index: 646705 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3384. Min Act: -0.1700
Data Index: 5061860 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3384. Min Act: -0.1700
Data Index: 8427262 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 3313959 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 6258455 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 3036266 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 7872374 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 2493012 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.2759. Min Act: -0.1700
Data Index: 5702452 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19