Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 728 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0710. Min Range: -7.0710
Max Act: 7.0710. Min Act: -0.1700
Data Index: 909373 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.8523. Min Act: -0.1700
Data Index: 2766608 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.8210. Min Act: -0.1700
Data Index: 828729 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.8210. Min Act: -0.1700
Data Index: 6064128 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.7898. Min Act: -0.1700
Data Index: 2137989 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.7585. Min Act: -0.1700
Data Index: 1083947 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.6960. Min Act: -0.1700
Data Index: 5098526 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.6335. Min Act: -0.1700
Data Index: 917999 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.6648. Min Act: -0.1700
Data Index: 3137244 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.6648. Min Act: -0.1700
Data Index: 4906825 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.6648. Min Act: -0.1700
Data Index: 5793577 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.6023. Min Act: -0.1700
Data Index: 5849113 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.6023. Min Act: -0.1700
Data Index: 6274318 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.5710. Min Act: -0.1700
Data Index: 3567473 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.5710. Min Act: -0.1700
Data Index: 5157122 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.5710. Min Act: -0.1700
Data Index: 5606694 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.5710. Min Act: -0.1700
Data Index: 2844323 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.4773. Min Act: -0.1700
Data Index: 290238 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.4773. Min Act: -0.1700
Data Index: 828728 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0710. Min Range: -7.0710
Max Act: 6.4773. Min Act: -0.1700
Data Index: 853624 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19