Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4062 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.8242. Min Act: -0.1700
Data Index: 886157 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.6992. Min Act: -0.1700
Data Index: 3762055 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.6679. Min Act: -0.1700
Data Index: 2157177 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.6367. Min Act: -0.1700
Data Index: 4076430 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.5429. Min Act: -0.1700
Data Index: 2065915 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.5742. Min Act: -0.1700
Data Index: 6851739 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.6054. Min Act: -0.1700
Data Index: 5683679 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.6054. Min Act: -0.1700
Data Index: 1575960 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.5429. Min Act: -0.1700
Data Index: 3089937 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.5117. Min Act: -0.1700
Data Index: 3232363 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.5117. Min Act: -0.1700
Data Index: 3453576 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.5429. Min Act: -0.1700
Data Index: 5022743 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.5117. Min Act: -0.1700
Data Index: 8475683 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.5117. Min Act: -0.1700
Data Index: 2110386 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.4492. Min Act: -0.1700
Data Index: 6908592 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.4492. Min Act: -0.1700
Data Index: 4495662 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.4179. Min Act: -0.1700
Data Index: 7033665 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.4804. Min Act: -0.1700
Data Index: 801176 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.4179. Min Act: -0.1700
Data Index: 4968386 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8242. Min Range: -4.8242
Max Act: 4.4492. Min Act: -0.1700
Data Index: 2001490 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19