Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1861. Min Range: -5.1861
Max Act: 5.1861. Min Act: -0.1700
Data Index: 8539930 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1861. Min Range: -5.1861
Max Act: 5.0924. Min Act: -0.1700
Data Index: 7443557 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.9361. Min Act: -0.1700
Data Index: 4489802 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.8111. Min Act: -0.1700
Data Index: 2507368 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.7799. Min Act: -0.1700
Data Index: 6649517 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.8111. Min Act: -0.1700
Data Index: 5600463 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.7486. Min Act: -0.1700
Data Index: 8704299 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.7486. Min Act: -0.1700
Data Index: 5604777 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.7486. Min Act: -0.1700
Data Index: 931581 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.7174. Min Act: -0.1700
Data Index: 7079771 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.6236. Min Act: -0.1700
Data Index: 3953914 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.6236. Min Act: -0.1700
Data Index: 4570333 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.6236. Min Act: -0.1700
Data Index: 2042415 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.6236. Min Act: -0.1700
Data Index: 1097588 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.6549. Min Act: -0.1700
Data Index: 3130938 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.5924. Min Act: -0.1700
Data Index: 2289907 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.5924. Min Act: -0.1700
Data Index: 435271 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.5299. Min Act: -0.1700
Data Index: 6649516 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.5299. Min Act: -0.1700
Data Index: 4676306 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1861. Min Range: -5.1861
Max Act: 4.5299. Min Act: -0.1700
Data Index: 4308328 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19