Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.7871. Min Act: -0.1700
Data Index: 3988811 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.5994. Min Act: -0.1700
Data Index: 1157066 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.5211. Min Act: -0.1700
Data Index: 251456 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.5368. Min Act: -0.1700
Data Index: 4667345 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4742. Min Act: -0.1700
Data Index: 5220134 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4898. Min Act: -0.1700
Data Index: 5045915 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4585. Min Act: -0.1700
Data Index: 6245534 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4742. Min Act: -0.1700
Data Index: 3468081 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4585. Min Act: -0.1700
Data Index: 7250931 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4585. Min Act: -0.1700
Data Index: 2414723 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4585. Min Act: -0.1700
Data Index: 2673195 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4428. Min Act: -0.1700
Data Index: 4927988 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4428. Min Act: -0.1700
Data Index: 5220137 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4271. Min Act: -0.1700
Data Index: 2824021 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4115. Min Act: -0.1700
Data Index: 1240746 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4271. Min Act: -0.1700
Data Index: 3823865 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4115. Min Act: -0.1700
Data Index: 2014063 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4115. Min Act: -0.1700
Data Index: 6427728 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.4271. Min Act: -0.1700
Data Index: 1015889 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7871. Min Range: -3.7871
Max Act: 3.3801. Min Act: -0.1700
Data Index: 5376402 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19