Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5476 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3055. Min Range: -7.3055
Max Act: 7.3055. Min Act: -0.1700
Data Index: 7682197 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3055. Min Range: -7.3055
Max Act: 7.2430. Min Act: -0.1700
Data Index: 5900248 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3055. Min Range: -7.3055
Max Act: 7.0555. Min Act: -0.1700
Data Index: 635057 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3055. Min Range: -7.3055
Max Act: 7.0243. Min Act: -0.1700
Data Index: 4053403 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.9930. Min Act: -0.1700
Data Index: 5326861 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.9930. Min Act: -0.1700
Data Index: 3574210 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.9305. Min Act: -0.1700
Data Index: 3521440 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.9305. Min Act: -0.1700
Data Index: 7580630 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.9305. Min Act: -0.1700
Data Index: 8258940 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.8993. Min Act: -0.1700
Data Index: 3697959 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.8680. Min Act: -0.1700
Data Index: 1017966 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.8680. Min Act: -0.1700
Data Index: 3727402 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.8055. Min Act: -0.1700
Data Index: 1577064 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.8055. Min Act: -0.1700
Data Index: 7559363 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.8055. Min Act: -0.1700
Data Index: 1828806 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.7743. Min Act: -0.1700
Data Index: 4084611 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.8055. Min Act: -0.1700
Data Index: 6198469 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.7430. Min Act: -0.1700
Data Index: 4647803 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.6805. Min Act: -0.1700
Data Index: 7424834 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3055. Min Range: -7.3055
Max Act: 6.7118. Min Act: -0.1700
Data Index: 747870 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19