Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6539. Min Range: -8.6539
Max Act: 8.6539. Min Act: -0.1700
Data Index: 2804380 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6539. Min Range: -8.6539
Max Act: 8.4664. Min Act: -0.1700
Data Index: 2017890 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6539. Min Range: -8.6539
Max Act: 8.2164. Min Act: -0.1700
Data Index: 3141074 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6539. Min Range: -8.6539
Max Act: 8.0914. Min Act: -0.1700
Data Index: 8622728 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6539. Min Range: -8.6539
Max Act: 8.0914. Min Act: -0.1700
Data Index: 706840 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.9039. Min Act: -0.1700
Data Index: 7244045 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.8414. Min Act: -0.1700
Data Index: 5754681 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.8102. Min Act: -0.1700
Data Index: 325127 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.8102. Min Act: -0.1700
Data Index: 8335048 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.7164. Min Act: -0.1700
Data Index: 2560631 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.6539. Min Act: -0.1700
Data Index: 4206986 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.6227. Min Act: -0.1700
Data Index: 7854190 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.5602. Min Act: -0.1700
Data Index: 8045291 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.5602. Min Act: -0.1700
Data Index: 3093639 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.5602. Min Act: -0.1700
Data Index: 1105847 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.5914. Min Act: -0.1700
Data Index: 5663637 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.5289. Min Act: -0.1700
Data Index: 4746454 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.4977. Min Act: -0.1700
Data Index: 7494415 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.5289. Min Act: -0.1700
Data Index: 3046050 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6539. Min Range: -8.6539
Max Act: 7.5289. Min Act: -0.1700
Data Index: 8335050 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19