Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 19.9305. Min Range: -19.9305
Max Act: 19.9305. Min Act: -0.1700
Data Index: 3729282 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.9305. Min Range: -19.9305
Max Act: 19.8055. Min Act: -0.1700
Data Index: 4665725 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.9305. Min Range: -19.9305
Max Act: 19.6805. Min Act: -0.1700
Data Index: 3729281 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.9305. Min Range: -19.9305
Max Act: 19.3055. Min Act: -0.1700
Data Index: 4665724 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.9305. Min Range: -19.9305
Max Act: 19.3055. Min Act: -0.1700
Data Index: 4483481 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.9305. Min Range: -19.9305
Max Act: 19.3055. Min Act: -0.1700
Data Index: 4665726 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.9305. Min Range: -19.9305
Max Act: 19.1805. Min Act: -0.1700
Data Index: 3729280 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.9305. Min Range: -19.9305
Max Act: 19.1805. Min Act: -0.1700
Data Index: 3729279 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.9305. Min Range: -19.9305
Max Act: 19.1805. Min Act: -0.1700
Data Index: 4483483 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.9305. Min Range: -19.9305
Max Act: 18.9305. Min Act: -0.1700
Data Index: 4483478 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.9305. Min Range: -19.9305
Max Act: 18.9305. Min Act: -0.1700
Data Index: 4665727 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.9305. Min Range: -19.9305
Max Act: 18.9305. Min Act: -0.1700
Data Index: 6969337 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.9305. Min Range: -19.9305
Max Act: 18.9305. Min Act: -0.1700
Data Index: 1672392 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.9305. Min Range: -19.9305
Max Act: 19.0555. Min Act: -0.1700
Data Index: 4665734 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.9305. Min Range: -19.9305
Max Act: 18.8055. Min Act: -0.1700
Data Index: 8560918 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.9305. Min Range: -19.9305
Max Act: 18.8055. Min Act: -0.1700
Data Index: 2711 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.9305. Min Range: -19.9305
Max Act: 18.8055. Min Act: -0.1700
Data Index: 2045211 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.9305. Min Range: -19.9305
Max Act: 18.8055. Min Act: -0.1700
Data Index: 8560917 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.9305. Min Range: -19.9305
Max Act: 18.6805. Min Act: -0.1700
Data Index: 1672391 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.9305. Min Range: -19.9305
Max Act: 18.6805. Min Act: -0.1700
Data Index: 4188608 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19