Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2780 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1575. Min Range: -8.1575
Max Act: 8.1575. Min Act: -0.1700
Data Index: 4058763 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.7513. Min Act: -0.1700
Data Index: 4470498 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.6888. Min Act: -0.1700
Data Index: 8093437 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.4700. Min Act: -0.1700
Data Index: 3961348 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.4700. Min Act: -0.1700
Data Index: 881084 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.4075. Min Act: -0.1700
Data Index: 300001 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.2200. Min Act: -0.1700
Data Index: 1766134 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.1888. Min Act: -0.1700
Data Index: 56565 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.2200. Min Act: -0.1700
Data Index: 6610887 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.2200. Min Act: -0.1700
Data Index: 8415027 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.1888. Min Act: -0.1700
Data Index: 5134511 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.2200. Min Act: -0.1700
Data Index: 5536985 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.1575. Min Act: -0.1700
Data Index: 7716455 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.1575. Min Act: -0.1700
Data Index: 1941612 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.1263. Min Act: -0.1700
Data Index: 1996396 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.0325. Min Act: -0.1700
Data Index: 4083197 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.0325. Min Act: -0.1700
Data Index: 5371390 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.0325. Min Act: -0.1700
Data Index: 7670050 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.0325. Min Act: -0.1700
Data Index: 7125756 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1575. Min Range: -8.1575
Max Act: 7.0013. Min Act: -0.1700
Data Index: 2559507 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19