Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4094 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.3032. Min Act: -0.1700
Data Index: 4943041 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.2868. Min Act: -0.1700
Data Index: 7660951 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.2373. Min Act: -0.1700
Data Index: 149001 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.2207. Min Act: -0.1700
Data Index: 2434476 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.2207. Min Act: -0.1700
Data Index: 8451678 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.2041. Min Act: -0.1700
Data Index: 3415183 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.2041. Min Act: -0.1700
Data Index: 3854788 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1875. Min Act: -0.1700
Data Index: 7331267 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1709. Min Act: -0.1700
Data Index: 1162811 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1709. Min Act: -0.1700
Data Index: 8221750 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1875. Min Act: -0.1700
Data Index: 4726714 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1875. Min Act: -0.1700
Data Index: 5747630 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1209. Min Act: -0.1700
Data Index: 4034901 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1376. Min Act: -0.1700
Data Index: 4046147 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1543. Min Act: -0.1700
Data Index: 1428993 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1209. Min Act: -0.1700
Data Index: 3031642 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1376. Min Act: -0.1700
Data Index: 3167370 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1209. Min Act: -0.1700
Data Index: 1380621 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1376. Min Act: -0.1700
Data Index: 3680971 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3032. Min Range: -2.3032
Max Act: 2.1376. Min Act: -0.1700
Data Index: 1706918 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19