Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 43 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.5055. Min Act: -0.1700
Data Index: 3009341 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.2242. Min Act: -0.1700
Data Index: 4242185 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.1930. Min Act: -0.1700
Data Index: 8407688 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.1930. Min Act: -0.1700
Data Index: 5296723 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.1617. Min Act: -0.1700
Data Index: 3609952 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.1305. Min Act: -0.1700
Data Index: 3673968 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.1305. Min Act: -0.1700
Data Index: 7710929 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.0992. Min Act: -0.1700
Data Index: 2484970 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.0992. Min Act: -0.1700
Data Index: 2598242 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.0367. Min Act: -0.1700
Data Index: 2833707 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.0055. Min Act: -0.1700
Data Index: 2983409 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.0055. Min Act: -0.1700
Data Index: 2591490 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5055. Min Range: -5.5055
Max Act: 5.0055. Min Act: -0.1700
Data Index: 6770395 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5055. Min Range: -5.5055
Max Act: 4.9742. Min Act: -0.1700
Data Index: 2442584 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5055. Min Range: -5.5055
Max Act: 4.9742. Min Act: -0.1700
Data Index: 6362949 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5055. Min Range: -5.5055
Max Act: 4.9742. Min Act: -0.1700
Data Index: 8004496 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5055. Min Range: -5.5055
Max Act: 4.9430. Min Act: -0.1700
Data Index: 4664928 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5055. Min Range: -5.5055
Max Act: 4.9430. Min Act: -0.1700
Data Index: 2088348 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5055. Min Range: -5.5055
Max Act: 4.9430. Min Act: -0.1700
Data Index: 2789203 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5055. Min Range: -5.5055
Max Act: 4.9430. Min Act: -0.1700
Data Index: 636494 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19