Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.8665. Min Act: -0.1700
Data Index: 4572783 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.8040. Min Act: -0.1700
Data Index: 2401864 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.7727. Min Act: -0.1700
Data Index: 6973354 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.7415. Min Act: -0.1700
Data Index: 6697069 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.7727. Min Act: -0.1700
Data Index: 4035260 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.6790. Min Act: -0.1700
Data Index: 2344472 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.6477. Min Act: -0.1700
Data Index: 4432432 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.6165. Min Act: -0.1700
Data Index: 647662 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.6165. Min Act: -0.1700
Data Index: 1208185 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.5540. Min Act: -0.1700
Data Index: 6565367 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.5540. Min Act: -0.1700
Data Index: 361807 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.5852. Min Act: -0.1700
Data Index: 6930890 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.5227. Min Act: -0.1700
Data Index: 8014223 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.5227. Min Act: -0.1700
Data Index: 3875062 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.5227. Min Act: -0.1700
Data Index: 8413742 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.4915. Min Act: -0.1700
Data Index: 3452953 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.4915. Min Act: -0.1700
Data Index: 5142034 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.4602. Min Act: -0.1700
Data Index: 4609069 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.4915. Min Act: -0.1700
Data Index: 2003765 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8665. Min Range: -4.8665
Max Act: 4.4602. Min Act: -0.1700
Data Index: 3143068 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19