Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3890 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3871. Min Range: -6.3871
Max Act: 6.3871. Min Act: -0.1700
Data Index: 4116113 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.9809. Min Act: -0.1700
Data Index: 1011872 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.9496. Min Act: -0.1700
Data Index: 536885 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.9496. Min Act: -0.1700
Data Index: 3147398 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.8871. Min Act: -0.1700
Data Index: 2433663 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.8246. Min Act: -0.1700
Data Index: 3092174 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.8246. Min Act: -0.1700
Data Index: 835523 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.7621. Min Act: -0.1700
Data Index: 5700202 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.7309. Min Act: -0.1700
Data Index: 2716890 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6996. Min Act: -0.1700
Data Index: 6261134 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6371. Min Act: -0.1700
Data Index: 5213158 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6684. Min Act: -0.1700
Data Index: 7312694 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6371. Min Act: -0.1700
Data Index: 6515181 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6371. Min Act: -0.1700
Data Index: 7305432 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6371. Min Act: -0.1700
Data Index: 5527045 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6059. Min Act: -0.1700
Data Index: 1822028 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6371. Min Act: -0.1700
Data Index: 6851029 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6059. Min Act: -0.1700
Data Index: 4407981 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6059. Min Act: -0.1700
Data Index: 3343567 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3871. Min Range: -6.3871
Max Act: 5.6059. Min Act: -0.1700
Data Index: 5741311 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19