Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 67 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.9019. Min Act: -0.1700
Data Index: 3963437 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.8707. Min Act: -0.1700
Data Index: 5518598 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6832. Min Act: -0.1700
Data Index: 1659342 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.5894. Min Act: -0.1700
Data Index: 5008665 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.5582. Min Act: -0.1700
Data Index: 4408697 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.4019. Min Act: -0.1700
Data Index: 4919106 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.3707. Min Act: -0.1700
Data Index: 8386352 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.3707. Min Act: -0.1700
Data Index: 4536921 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.3707. Min Act: -0.1700
Data Index: 6261608 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.3707. Min Act: -0.1700
Data Index: 365884 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.2769. Min Act: -0.1700
Data Index: 8752006 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.2144. Min Act: -0.1700
Data Index: 843770 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.1832. Min Act: -0.1700
Data Index: 8415162 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.1207. Min Act: -0.1700
Data Index: 7747758 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.0894. Min Act: -0.1700
Data Index: 8508771 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.1207. Min Act: -0.1700
Data Index: 7605089 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.1207. Min Act: -0.1700
Data Index: 7051386 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.0894. Min Act: -0.1700
Data Index: 1515075 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.0582. Min Act: -0.1700
Data Index: 7220250 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.1207. Min Act: -0.1700
Data Index: 4859203 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19