Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5910 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0628. Min Range: -5.0628
Max Act: 5.0628. Min Act: -0.1700
Data Index: 3683834 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.8440. Min Act: -0.1700
Data Index: 1009491 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.8128. Min Act: -0.1700
Data Index: 7474046 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.8128. Min Act: -0.1700
Data Index: 4876511 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.8128. Min Act: -0.1700
Data Index: 3844576 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.7815. Min Act: -0.1700
Data Index: 4944880 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.7503. Min Act: -0.1700
Data Index: 3875998 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.6878. Min Act: -0.1700
Data Index: 362206 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.6878. Min Act: -0.1700
Data Index: 6586420 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.6878. Min Act: -0.1700
Data Index: 3158843 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.6565. Min Act: -0.1700
Data Index: 362208 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.6565. Min Act: -0.1700
Data Index: 5993007 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.6565. Min Act: -0.1700
Data Index: 6779445 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.6565. Min Act: -0.1700
Data Index: 7802771 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.6565. Min Act: -0.1700
Data Index: 7719976 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.6253. Min Act: -0.1700
Data Index: 8171726 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.5940. Min Act: -0.1700
Data Index: 2215299 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.5628. Min Act: -0.1700
Data Index: 1101023 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.5628. Min Act: -0.1700
Data Index: 4742215 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0628. Min Range: -5.0628
Max Act: 4.5628. Min Act: -0.1700
Data Index: 4132580 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19