Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.2789. Min Act: -0.1700
Data Index: 8249683 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.1539. Min Act: -0.1700
Data Index: 8441350 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.1227. Min Act: -0.1700
Data Index: 2275196 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.1539. Min Act: -0.1700
Data Index: 2491047 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.0914. Min Act: -0.1700
Data Index: 3419980 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.0914. Min Act: -0.1700
Data Index: 5415339 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.0914. Min Act: -0.1700
Data Index: 2856689 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.0289. Min Act: -0.1700
Data Index: 1128611 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.0602. Min Act: -0.1700
Data Index: 3435090 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.0602. Min Act: -0.1700
Data Index: 1128610 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.0602. Min Act: -0.1700
Data Index: 838382 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2789. Min Range: -5.2789
Max Act: 5.0289. Min Act: -0.1700
Data Index: 6756665 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2789. Min Range: -5.2789
Max Act: 4.9977. Min Act: -0.1700
Data Index: 3131168 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2789. Min Range: -5.2789
Max Act: 4.9977. Min Act: -0.1700
Data Index: 6318593 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2789. Min Range: -5.2789
Max Act: 4.9977. Min Act: -0.1700
Data Index: 8429954 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2789. Min Range: -5.2789
Max Act: 4.9977. Min Act: -0.1700
Data Index: 3844648 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2789. Min Range: -5.2789
Max Act: 4.9977. Min Act: -0.1700
Data Index: 5562418 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2789. Min Range: -5.2789
Max Act: 4.9977. Min Act: -0.1700
Data Index: 2850848 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2789. Min Range: -5.2789
Max Act: 4.9977. Min Act: -0.1700
Data Index: 1442497 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2789. Min Range: -5.2789
Max Act: 4.9664. Min Act: -0.1700
Data Index: 3967279 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19