Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6345 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.9905. Min Act: -0.1700
Data Index: 1611283 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.9280. Min Act: -0.1700
Data Index: 274872 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.8342. Min Act: -0.1700
Data Index: 4385646 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.7717. Min Act: -0.1700
Data Index: 6221446 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.7717. Min Act: -0.1700
Data Index: 5884297 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.7717. Min Act: -0.1700
Data Index: 5688308 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.7405. Min Act: -0.1700
Data Index: 711508 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.7405. Min Act: -0.1700
Data Index: 5389791 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.7092. Min Act: -0.1700
Data Index: 5587712 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.6467. Min Act: -0.1700
Data Index: 2374423 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.6780. Min Act: -0.1700
Data Index: 2054774 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.6780. Min Act: -0.1700
Data Index: 3019561 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.6780. Min Act: -0.1700
Data Index: 661782 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.6780. Min Act: -0.1700
Data Index: 7137026 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.6155. Min Act: -0.1700
Data Index: 48465 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.6155. Min Act: -0.1700
Data Index: 7476318 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.6155. Min Act: -0.1700
Data Index: 379327 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.5530. Min Act: -0.1700
Data Index: 884025 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.5842. Min Act: -0.1700
Data Index: 5450116 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9905. Min Range: -6.9905
Max Act: 6.5842. Min Act: -0.1700
Data Index: 919961 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19