Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1043 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.8111. Min Act: -0.1700
Data Index: 1895297 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7799. Min Act: -0.1700
Data Index: 4193248 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7799. Min Act: -0.1700
Data Index: 7708795 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7486. Min Act: -0.1700
Data Index: 8273124 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7486. Min Act: -0.1700
Data Index: 7698652 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7174. Min Act: -0.1700
Data Index: 6885562 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7174. Min Act: -0.1700
Data Index: 2719130 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7486. Min Act: -0.1700
Data Index: 800796 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.6549. Min Act: -0.1700
Data Index: 8647338 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7174. Min Act: -0.1700
Data Index: 7941409 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.6236. Min Act: -0.1700
Data Index: 6707190 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5924. Min Act: -0.1700
Data Index: 4641571 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5924. Min Act: -0.1700
Data Index: 4222551 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5611. Min Act: -0.1700
Data Index: 2002087 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5924. Min Act: -0.1700
Data Index: 8312046 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5611. Min Act: -0.1700
Data Index: 2885306 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5924. Min Act: -0.1700
Data Index: 6591677 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5611. Min Act: -0.1700
Data Index: 3473674 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.4986. Min Act: -0.1700
Data Index: 767829 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5299. Min Act: -0.1700
Data Index: 1816424 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19