Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 379 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.7096. Min Act: -0.1700
Data Index: 7742918 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.6471. Min Act: -0.1700
Data Index: 2308663 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.5221. Min Act: -0.1700
Data Index: 7437370 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.4596. Min Act: -0.1700
Data Index: 1669724 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.3971. Min Act: -0.1700
Data Index: 8338101 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.3971. Min Act: -0.1700
Data Index: 2362964 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.3971. Min Act: -0.1700
Data Index: 1858897 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.3346. Min Act: -0.1700
Data Index: 1578085 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.3346. Min Act: -0.1700
Data Index: 1099100 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.3346. Min Act: -0.1700
Data Index: 2736152 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.3346. Min Act: -0.1700
Data Index: 7784218 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.3346. Min Act: -0.1700
Data Index: 223511 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.2721. Min Act: -0.1700
Data Index: 3060693 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.2721. Min Act: -0.1700
Data Index: 1626307 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.2096. Min Act: -0.1700
Data Index: 6966874 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.2096. Min Act: -0.1700
Data Index: 5512505 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.2096. Min Act: -0.1700
Data Index: 8704307 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.1471. Min Act: -0.1700
Data Index: 5206296 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.1471. Min Act: -0.1700
Data Index: 3056956 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7096. Min Range: -8.7096
Max Act: 8.1471. Min Act: -0.1700
Data Index: 4416139 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19