Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 231 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4596. Min Range: -5.4596
Max Act: 5.4596. Min Act: -0.1700
Data Index: 1851592 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4596. Min Range: -5.4596
Max Act: 5.3346. Min Act: -0.1700
Data Index: 2282500 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4596. Min Range: -5.4596
Max Act: 5.1784. Min Act: -0.1700
Data Index: 5660654 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4596. Min Range: -5.4596
Max Act: 5.1784. Min Act: -0.1700
Data Index: 6458573 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4596. Min Range: -5.4596
Max Act: 5.0221. Min Act: -0.1700
Data Index: 2119859 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4596. Min Range: -5.4596
Max Act: 5.0221. Min Act: -0.1700
Data Index: 3664362 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4596. Min Range: -5.4596
Max Act: 5.0221. Min Act: -0.1700
Data Index: 3653954 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4596. Min Range: -5.4596
Max Act: 5.0221. Min Act: -0.1700
Data Index: 4091761 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4596. Min Range: -5.4596
Max Act: 5.0221. Min Act: -0.1700
Data Index: 5340993 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4596. Min Range: -5.4596
Max Act: 5.0221. Min Act: -0.1700
Data Index: 8503760 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4596. Min Range: -5.4596
Max Act: 4.9909. Min Act: -0.1700
Data Index: 7730219 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4596. Min Range: -5.4596
Max Act: 4.9909. Min Act: -0.1700
Data Index: 2315416 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4596. Min Range: -5.4596
Max Act: 4.9909. Min Act: -0.1700
Data Index: 5172101 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4596. Min Range: -5.4596
Max Act: 4.9909. Min Act: -0.1700
Data Index: 3770786 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4596. Min Range: -5.4596
Max Act: 4.9596. Min Act: -0.1700
Data Index: 7286315 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4596. Min Range: -5.4596
Max Act: 4.9284. Min Act: -0.1700
Data Index: 8575331 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4596. Min Range: -5.4596
Max Act: 4.9284. Min Act: -0.1700
Data Index: 7571899 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4596. Min Range: -5.4596
Max Act: 4.8971. Min Act: -0.1700
Data Index: 1348998 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4596. Min Range: -5.4596
Max Act: 4.9284. Min Act: -0.1700
Data Index: 8371704 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4596. Min Range: -5.4596
Max Act: 4.8971. Min Act: -0.1700
Data Index: 8198420 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19