Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4353 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4318. Min Range: -8.4318
Max Act: 8.4318. Min Act: -0.1700
Data Index: 8051647 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4318. Min Range: -8.4318
Max Act: 8.1818. Min Act: -0.1700
Data Index: 8081699 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4318. Min Range: -8.4318
Max Act: 8.2130. Min Act: -0.1700
Data Index: 5120345 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4318. Min Range: -8.4318
Max Act: 8.1818. Min Act: -0.1700
Data Index: 265495 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4318. Min Range: -8.4318
Max Act: 8.1193. Min Act: -0.1700
Data Index: 2026592 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4318. Min Range: -8.4318
Max Act: 8.1193. Min Act: -0.1700
Data Index: 2169479 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4318. Min Range: -8.4318
Max Act: 8.0255. Min Act: -0.1700
Data Index: 5360443 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4318. Min Range: -8.4318
Max Act: 8.0255. Min Act: -0.1700
Data Index: 428094 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4318. Min Range: -8.4318
Max Act: 8.0255. Min Act: -0.1700
Data Index: 5381084 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9943. Min Act: -0.1700
Data Index: 8320266 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9630. Min Act: -0.1700
Data Index: 3026837 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9630. Min Act: -0.1700
Data Index: 6061985 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9630. Min Act: -0.1700
Data Index: 1617958 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9630. Min Act: -0.1700
Data Index: 12416 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9630. Min Act: -0.1700
Data Index: 449541 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9943. Min Act: -0.1700
Data Index: 3971840 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9318. Min Act: -0.1700
Data Index: 4808827 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9005. Min Act: -0.1700
Data Index: 5306205 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9318. Min Act: -0.1700
Data Index: 5547526 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4318. Min Range: -8.4318
Max Act: 7.9005. Min Act: -0.1700
Data Index: 1806684 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19