Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3300 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0397. Min Range: -7.0397
Max Act: 7.0397. Min Act: -0.1700
Data Index: 5851430 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.8209. Min Act: -0.1700
Data Index: 1554838 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.8209. Min Act: -0.1700
Data Index: 6620334 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.7897. Min Act: -0.1700
Data Index: 7579258 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.8209. Min Act: -0.1700
Data Index: 6712036 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.7897. Min Act: -0.1700
Data Index: 811486 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.7272. Min Act: -0.1700
Data Index: 6495560 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.6959. Min Act: -0.1700
Data Index: 1905283 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.6959. Min Act: -0.1700
Data Index: 1055515 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.6647. Min Act: -0.1700
Data Index: 6838838 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.6959. Min Act: -0.1700
Data Index: 5695913 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.6647. Min Act: -0.1700
Data Index: 7177781 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.6022. Min Act: -0.1700
Data Index: 2733820 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.6022. Min Act: -0.1700
Data Index: 6526851 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.5709. Min Act: -0.1700
Data Index: 443590 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.5397. Min Act: -0.1700
Data Index: 2026716 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.5709. Min Act: -0.1700
Data Index: 7212054 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.5397. Min Act: -0.1700
Data Index: 6082044 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.5397. Min Act: -0.1700
Data Index: 2773955 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0397. Min Range: -7.0397
Max Act: 6.5397. Min Act: -0.1700
Data Index: 1876942 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19