Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8734. Min Act: -0.1700
Data Index: 4271635 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8109. Min Act: -0.1700
Data Index: 6950716 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.7796. Min Act: -0.1700
Data Index: 1973529 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.5762. Min Act: -0.1700
Data Index: 647158 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.5762. Min Act: -0.1700
Data Index: 1358137 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.5605. Min Act: -0.1700
Data Index: 7728408 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.5762. Min Act: -0.1700
Data Index: 4207478 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4509. Min Act: -0.1700
Data Index: 1259448 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4509. Min Act: -0.1700
Data Index: 3805396 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4666. Min Act: -0.1700
Data Index: 8224712 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4196. Min Act: -0.1700
Data Index: 7374100 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4196. Min Act: -0.1700
Data Index: 1936504 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4039. Min Act: -0.1700
Data Index: 4405117 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4352. Min Act: -0.1700
Data Index: 7062867 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4196. Min Act: -0.1700
Data Index: 4030448 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4352. Min Act: -0.1700
Data Index: 4187520 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.3882. Min Act: -0.1700
Data Index: 3783104 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4352. Min Act: -0.1700
Data Index: 2016957 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4196. Min Act: -0.1700
Data Index: 6667863 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.4039. Min Act: -0.1700
Data Index: 8619021 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19