Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4107 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.8890. Min Act: -0.1700
Data Index: 5615039 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.8265. Min Act: -0.1700
Data Index: 543314 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.7328. Min Act: -0.1700
Data Index: 4151108 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.7328. Min Act: -0.1700
Data Index: 3326501 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.7328. Min Act: -0.1700
Data Index: 1363705 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.7328. Min Act: -0.1700
Data Index: 7198249 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.7015. Min Act: -0.1700
Data Index: 1858898 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.7015. Min Act: -0.1700
Data Index: 5937267 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.6703. Min Act: -0.1700
Data Index: 50057 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.6703. Min Act: -0.1700
Data Index: 887476 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.6390. Min Act: -0.1700
Data Index: 5340324 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.6390. Min Act: -0.1700
Data Index: 6589297 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.6390. Min Act: -0.1700
Data Index: 7982173 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.6078. Min Act: -0.1700
Data Index: 5882472 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.6078. Min Act: -0.1700
Data Index: 1977775 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.6390. Min Act: -0.1700
Data Index: 6301773 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.6078. Min Act: -0.1700
Data Index: 6672422 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.5765. Min Act: -0.1700
Data Index: 5882473 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.5765. Min Act: -0.1700
Data Index: 2815391 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8890. Min Range: -4.8890
Max Act: 4.5453. Min Act: -0.1700
Data Index: 424755 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19