Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.9853. Min Act: -0.1700
Data Index: 1405986 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.9540. Min Act: -0.1700
Data Index: 3505340 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.8602. Min Act: -0.1700
Data Index: 4620695 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.8289. Min Act: -0.1700
Data Index: 1938276 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.8289. Min Act: -0.1700
Data Index: 7160174 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.7195. Min Act: -0.1700
Data Index: 2749841 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.6882. Min Act: -0.1700
Data Index: 2165244 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.6569. Min Act: -0.1700
Data Index: 554083 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.6882. Min Act: -0.1700
Data Index: 2809804 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.6725. Min Act: -0.1700
Data Index: 651357 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.6256. Min Act: -0.1700
Data Index: 3749776 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.5630. Min Act: -0.1700
Data Index: 5822776 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.6256. Min Act: -0.1700
Data Index: 8609881 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.5630. Min Act: -0.1700
Data Index: 2086863 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.5786. Min Act: -0.1700
Data Index: 4555614 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.6412. Min Act: -0.1700
Data Index: 2876413 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.6099. Min Act: -0.1700
Data Index: 4387825 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.5473. Min Act: -0.1700
Data Index: 8468523 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.5786. Min Act: -0.1700
Data Index: 3825422 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9853. Min Range: -3.9853
Max Act: 3.5786. Min Act: -0.1700
Data Index: 3361526 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19