Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4678 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3006. Min Range: -6.3006
Max Act: 6.3006. Min Act: -0.1700
Data Index: 4944448 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3006. Min Range: -6.3006
Max Act: 6.2381. Min Act: -0.1700
Data Index: 8035349 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3006. Min Range: -6.3006
Max Act: 6.2068. Min Act: -0.1700
Data Index: 1074419 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3006. Min Range: -6.3006
Max Act: 6.0193. Min Act: -0.1700
Data Index: 6202555 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.9881. Min Act: -0.1700
Data Index: 1874094 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.9881. Min Act: -0.1700
Data Index: 5936208 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.9568. Min Act: -0.1700
Data Index: 7956431 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8943. Min Act: -0.1700
Data Index: 1053681 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8943. Min Act: -0.1700
Data Index: 931002 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8631. Min Act: -0.1700
Data Index: 4292908 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8318. Min Act: -0.1700
Data Index: 2019018 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8318. Min Act: -0.1700
Data Index: 2003431 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8006. Min Act: -0.1700
Data Index: 8374333 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8006. Min Act: -0.1700
Data Index: 6369442 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8318. Min Act: -0.1700
Data Index: 6182217 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8006. Min Act: -0.1700
Data Index: 2313808 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8006. Min Act: -0.1700
Data Index: 663229 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.8318. Min Act: -0.1700
Data Index: 668369 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.7693. Min Act: -0.1700
Data Index: 5353280 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3006. Min Range: -6.3006
Max Act: 5.7693. Min Act: -0.1700
Data Index: 3576324 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19