Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1744 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.6979. Min Act: -0.1700
Data Index: 5849338 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.6354. Min Act: -0.1700
Data Index: 7408961 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.6667. Min Act: -0.1700
Data Index: 4581835 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.6042. Min Act: -0.1700
Data Index: 1413601 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.5104. Min Act: -0.1700
Data Index: 1848478 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.5104. Min Act: -0.1700
Data Index: 4288968 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.4792. Min Act: -0.1700
Data Index: 2226718 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.4167. Min Act: -0.1700
Data Index: 8447757 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.4167. Min Act: -0.1700
Data Index: 5925742 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.4167. Min Act: -0.1700
Data Index: 6638039 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.4167. Min Act: -0.1700
Data Index: 3128999 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.4167. Min Act: -0.1700
Data Index: 18731 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.4167. Min Act: -0.1700
Data Index: 4170119 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.3542. Min Act: -0.1700
Data Index: 4112592 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.2917. Min Act: -0.1700
Data Index: 8036715 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.2917. Min Act: -0.1700
Data Index: 8346547 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.2917. Min Act: -0.1700
Data Index: 1907551 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.2917. Min Act: -0.1700
Data Index: 3226842 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.2917. Min Act: -0.1700
Data Index: 4821115 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6979. Min Range: -6.6979
Max Act: 6.2292. Min Act: -0.1700
Data Index: 4416690 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19