Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.9291. Min Act: -0.1700
Data Index: 1774040 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.4604. Min Act: -0.1698
Data Index: 217643 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.4291. Min Act: -0.1700
Data Index: 3951596 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.4291. Min Act: -0.1700
Data Index: 3951597 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.3666. Min Act: -0.1700
Data Index: 1774036 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.3041. Min Act: -0.1700
Data Index: 6280926 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.3041. Min Act: -0.1700
Data Index: 3917725 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.2728. Min Act: -0.1700
Data Index: 1768197 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.2103. Min Act: -0.1700
Data Index: 6460355 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.1791. Min Act: -0.1700
Data Index: 7997658 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.1791. Min Act: -0.1700
Data Index: 1774037 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.1791. Min Act: -0.1700
Data Index: 1717275 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.1791. Min Act: -0.1700
Data Index: 3010387 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.1478. Min Act: -0.1700
Data Index: 6936870 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.1478. Min Act: -0.1700
Data Index: 1898128 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.1478. Min Act: -0.1700
Data Index: 7588430 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.1166. Min Act: -0.1700
Data Index: 5028831 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.1166. Min Act: -0.1700
Data Index: 6936886 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.0853. Min Act: -0.1700
Data Index: 2339482 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9291. Min Range: -4.9291
Max Act: 4.0853. Min Act: -0.1700
Data Index: 1774030 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19