Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3024. Min Range: -4.3024
Max Act: 4.3024. Min Act: -0.1700
Data Index: 1527390 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3024. Min Range: -4.3024
Max Act: 4.2711. Min Act: -0.1700
Data Index: 8078502 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3024. Min Range: -4.3024
Max Act: 4.1774. Min Act: -0.1700
Data Index: 174079 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3024. Min Range: -4.3024
Max Act: 4.1148. Min Act: -0.1700
Data Index: 8568730 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3024. Min Range: -4.3024
Max Act: 4.0523. Min Act: -0.1700
Data Index: 6797232 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3024. Min Range: -4.3024
Max Act: 4.0523. Min Act: -0.1700
Data Index: 4623630 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3024. Min Range: -4.3024
Max Act: 4.0211. Min Act: -0.1700
Data Index: 8353782 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3024. Min Range: -4.3024
Max Act: 4.0211. Min Act: -0.1700
Data Index: 4623631 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3024. Min Range: -4.3024
Max Act: 4.0211. Min Act: -0.1700
Data Index: 4527783 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9898. Min Act: -0.1700
Data Index: 4180013 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9586. Min Act: -0.1700
Data Index: 7982168 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9586. Min Act: -0.1700
Data Index: 7976281 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9586. Min Act: -0.1700
Data Index: 8078503 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9586. Min Act: -0.1700
Data Index: 7311344 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9586. Min Act: -0.1700
Data Index: 6833832 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9586. Min Act: -0.1700
Data Index: 6797235 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9898. Min Act: -0.1700
Data Index: 531190 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9586. Min Act: -0.1700
Data Index: 2550321 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9273. Min Act: -0.1700
Data Index: 6209707 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3024. Min Range: -4.3024
Max Act: 3.9586. Min Act: -0.1700
Data Index: 8328270 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19