Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2779 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1591. Min Range: -7.1591
Max Act: 7.1591. Min Act: -0.1700
Data Index: 366584 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1591. Min Range: -7.1591
Max Act: 7.0029. Min Act: -0.1700
Data Index: 5104719 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.9404. Min Act: -0.1700
Data Index: 363803 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.9091. Min Act: -0.1700
Data Index: 6846905 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.5029. Min Act: -0.1700
Data Index: 2391523 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.4404. Min Act: -0.1700
Data Index: 3705520 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.4404. Min Act: -0.1700
Data Index: 5056697 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.4091. Min Act: -0.1700
Data Index: 7796427 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.3779. Min Act: -0.1700
Data Index: 6980470 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.3779. Min Act: -0.1700
Data Index: 232531 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.3154. Min Act: -0.1700
Data Index: 2334662 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.2841. Min Act: -0.1700
Data Index: 760509 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.2529. Min Act: -0.1700
Data Index: 2644764 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.1904. Min Act: -0.1700
Data Index: 951728 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.1904. Min Act: -0.1700
Data Index: 3558950 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.1279. Min Act: -0.1700
Data Index: 125338 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.1591. Min Act: -0.1700
Data Index: 355096 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.1591. Min Act: -0.1700
Data Index: 4841927 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.1279. Min Act: -0.1700
Data Index: 2870249 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1591. Min Range: -7.1591
Max Act: 6.0966. Min Act: -0.1700
Data Index: 7511762 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19