Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0938. Min Range: -8.0938
Max Act: 8.0938. Min Act: -0.1700
Data Index: 97429 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0938. Min Range: -8.0938
Max Act: 8.0938. Min Act: -0.1700
Data Index: 4520849 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.8438. Min Act: -0.1700
Data Index: 2312417 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.8438. Min Act: -0.1700
Data Index: 5383456 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.7813. Min Act: -0.1700
Data Index: 7964899 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.7813. Min Act: -0.1700
Data Index: 2267301 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.7813. Min Act: -0.1700
Data Index: 8007410 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.7188. Min Act: -0.1699
Data Index: 1702813 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.6563. Min Act: -0.1700
Data Index: 6236377 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.6563. Min Act: -0.1700
Data Index: 5243438 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.6563. Min Act: -0.1700
Data Index: 1386244 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.5938. Min Act: -0.1700
Data Index: 3586285 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.5938. Min Act: -0.1700
Data Index: 6733144 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.5313. Min Act: -0.1700
Data Index: 8275861 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.5313. Min Act: -0.1700
Data Index: 6305414 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.5313. Min Act: -0.1700
Data Index: 3698640 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.5000. Min Act: -0.1700
Data Index: 7487944 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.5000. Min Act: -0.1700
Data Index: 1963571 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.5000. Min Act: -0.1700
Data Index: 4628578 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0938. Min Range: -8.0938
Max Act: 7.4688. Min Act: -0.1700
Data Index: 517022 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19