Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.5781. Min Act: -0.1700
Data Index: 4227906 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.5156. Min Act: -0.1700
Data Index: 1389874 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.4531. Min Act: -0.1700
Data Index: 787258 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.3906. Min Act: -0.1700
Data Index: 4421935 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.2969. Min Act: -0.1700
Data Index: 8116930 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.3281. Min Act: -0.1700
Data Index: 7124791 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.3281. Min Act: -0.1700
Data Index: 5621698 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.3281. Min Act: -0.1700
Data Index: 672965 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.2969. Min Act: -0.1700
Data Index: 7854508 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.2969. Min Act: -0.1700
Data Index: 366714 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.2656. Min Act: -0.1700
Data Index: 1981383 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.2969. Min Act: -0.1700
Data Index: 6693780 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.2344. Min Act: -0.1700
Data Index: 1134059 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.2656. Min Act: -0.1700
Data Index: 148721 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.2344. Min Act: -0.1700
Data Index: 3799283 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.1719. Min Act: -0.1700
Data Index: 4867249 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.2031. Min Act: -0.1700
Data Index: 8449612 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.1719. Min Act: -0.1700
Data Index: 2113428 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.1719. Min Act: -0.1700
Data Index: 4489980 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5781. Min Range: -4.5781
Max Act: 4.1719. Min Act: -0.1700
Data Index: 7111433 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19