Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3599 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.7992. Min Act: -0.1700
Data Index: 7578901 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.7679. Min Act: -0.1700
Data Index: 7482550 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.6742. Min Act: -0.1700
Data Index: 1491516 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.6429. Min Act: -0.1700
Data Index: 4501070 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.6429. Min Act: -0.1700
Data Index: 2917571 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.5492. Min Act: -0.1700
Data Index: 1322234 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.4867. Min Act: -0.1700
Data Index: 231287 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.4867. Min Act: -0.1700
Data Index: 4880933 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.4554. Min Act: -0.1700
Data Index: 3715273 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.4242. Min Act: -0.1700
Data Index: 5395980 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.3929. Min Act: -0.1700
Data Index: 592105 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.3617. Min Act: -0.1700
Data Index: 5105090 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.3304. Min Act: -0.1700
Data Index: 6511730 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.3304. Min Act: -0.1700
Data Index: 6397449 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.3304. Min Act: -0.1700
Data Index: 4026573 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.2679. Min Act: -0.1700
Data Index: 1647990 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.2679. Min Act: -0.1700
Data Index: 7524444 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.2679. Min Act: -0.1700
Data Index: 3924698 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.2679. Min Act: -0.1700
Data Index: 6966734 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7992. Min Range: -5.7992
Max Act: 5.2367. Min Act: -0.1700
Data Index: 2076989 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19