Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 700 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1055. Min Range: -4.1055
Max Act: 4.1055. Min Act: -0.1700
Data Index: 3074982 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1055. Min Range: -4.1055
Max Act: 4.0430. Min Act: -0.1700
Data Index: 3384666 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.9805. Min Act: -0.1700
Data Index: 1330948 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.9492. Min Act: -0.1700
Data Index: 1473236 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.9492. Min Act: -0.1700
Data Index: 3084710 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.8867. Min Act: -0.1700
Data Index: 2014446 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.8242. Min Act: -0.1700
Data Index: 6145310 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.8554. Min Act: -0.1700
Data Index: 5315534 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.7929. Min Act: -0.1700
Data Index: 4777587 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.8242. Min Act: -0.1700
Data Index: 5537344 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.7929. Min Act: -0.1700
Data Index: 4296592 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.7147. Min Act: -0.1700
Data Index: 8219097 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.7147. Min Act: -0.1700
Data Index: 6776575 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.6991. Min Act: -0.1700
Data Index: 6170476 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.6991. Min Act: -0.1700
Data Index: 8616075 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.6834. Min Act: -0.1700
Data Index: 2268800 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.6991. Min Act: -0.1700
Data Index: 1380590 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.7147. Min Act: -0.1700
Data Index: 8810776 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.6678. Min Act: -0.1700
Data Index: 2615369 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1055. Min Range: -4.1055
Max Act: 3.6834. Min Act: -0.1700
Data Index: 5191823 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19