Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 960 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4481. Min Range: -8.4481
Max Act: 8.4481. Min Act: -0.1700
Data Index: 3057481 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4481. Min Range: -8.4481
Max Act: 8.1981. Min Act: -0.1700
Data Index: 4499350 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4481. Min Range: -8.4481
Max Act: 8.1356. Min Act: -0.1700
Data Index: 1048163 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4481. Min Range: -8.4481
Max Act: 8.0731. Min Act: -0.1700
Data Index: 2779151 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4481. Min Range: -8.4481
Max Act: 8.0419. Min Act: -0.1700
Data Index: 4162359 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.9481. Min Act: -0.1700
Data Index: 5902432 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.8231. Min Act: -0.1700
Data Index: 6168433 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.8231. Min Act: -0.1700
Data Index: 4442721 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.7606. Min Act: -0.1700
Data Index: 4742283 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.7294. Min Act: -0.1700
Data Index: 3645119 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.6981. Min Act: -0.1700
Data Index: 7972507 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.6669. Min Act: -0.1700
Data Index: 5309449 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.6356. Min Act: -0.1700
Data Index: 793607 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.6356. Min Act: -0.1700
Data Index: 1409392 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.6356. Min Act: -0.1700
Data Index: 5984007 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.5731. Min Act: -0.1700
Data Index: 2735815 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.6044. Min Act: -0.1700
Data Index: 8396121 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.5731. Min Act: -0.1700
Data Index: 732185 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.5419. Min Act: -0.1700
Data Index: 1119026 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4481. Min Range: -8.4481
Max Act: 7.5419. Min Act: -0.1700
Data Index: 1580428 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19