Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2144 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4167. Min Range: -9.4167
Max Act: 9.4167. Min Act: -0.1700
Data Index: 2351204 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4167. Min Range: -9.4167
Max Act: 9.2917. Min Act: -0.1700
Data Index: 3341732 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.7292. Min Act: -0.1700
Data Index: 3032990 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.6667. Min Act: -0.1700
Data Index: 7916974 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.6667. Min Act: -0.1700
Data Index: 224915 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.5417. Min Act: -0.1700
Data Index: 1049197 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.4792. Min Act: -0.1700
Data Index: 1072592 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.4792. Min Act: -0.1700
Data Index: 4116124 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.4167. Min Act: -0.1700
Data Index: 8128268 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.3542. Min Act: -0.1700
Data Index: 5224509 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.3542. Min Act: -0.1700
Data Index: 3067568 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.3542. Min Act: -0.1700
Data Index: 4552982 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.3542. Min Act: -0.1700
Data Index: 6696965 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.2917. Min Act: -0.1700
Data Index: 1064303 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.2917. Min Act: -0.1700
Data Index: 1653714 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.2292. Min Act: -0.1700
Data Index: 5398292 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.2917. Min Act: -0.1700
Data Index: 8215425 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.2292. Min Act: -0.1700
Data Index: 5900866 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.2292. Min Act: -0.1700
Data Index: 3550337 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4167. Min Range: -9.4167
Max Act: 8.1667. Min Act: -0.1700
Data Index: 5478210 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19