Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.8910. Min Act: -0.1700
Data Index: 4905258 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.7973. Min Act: -0.1700
Data Index: 4760792 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.7348. Min Act: -0.1700
Data Index: 3060791 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.7348. Min Act: -0.1700
Data Index: 2295901 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.7348. Min Act: -0.1700
Data Index: 3060792 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.5785. Min Act: -0.1700
Data Index: 749014 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.4848. Min Act: -0.1700
Data Index: 4812249 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.5160. Min Act: -0.1700
Data Index: 514299 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.4223. Min Act: -0.1700
Data Index: 6322502 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.3910. Min Act: -0.1700
Data Index: 4479583 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.4535. Min Act: -0.1700
Data Index: 5849912 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.4223. Min Act: -0.1700
Data Index: 2205585 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.3285. Min Act: -0.1700
Data Index: 2268105 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.3598. Min Act: -0.1700
Data Index: 5704790 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.3910. Min Act: -0.1700
Data Index: 5482086 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.3285. Min Act: -0.1700
Data Index: 8073510 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.3285. Min Act: -0.1700
Data Index: 51190 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.3285. Min Act: -0.1700
Data Index: 879927 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.3285. Min Act: -0.1700
Data Index: 3178649 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8910. Min Range: -7.8910
Max Act: 7.2660. Min Act: -0.1700
Data Index: 2731062 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19