Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.9658. Min Act: -0.1700
Data Index: 2845227 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0283. Min Range: -9.0283
Max Act: 9.0283. Min Act: -0.1700
Data Index: 2275255 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0283. Min Range: -9.0283
Max Act: 9.0283. Min Act: -0.1700
Data Index: 7891962 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.9033. Min Act: -0.1700
Data Index: 1496040 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.9658. Min Act: -0.1700
Data Index: 3089531 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.9033. Min Act: -0.1700
Data Index: 2967229 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.7783. Min Act: -0.1700
Data Index: 1577993 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.7783. Min Act: -0.1700
Data Index: 5606112 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.7783. Min Act: -0.1700
Data Index: 8801945 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.7783. Min Act: -0.1700
Data Index: 70105 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.6533. Min Act: -0.1700
Data Index: 5359100 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.7158. Min Act: -0.1700
Data Index: 6311347 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.6533. Min Act: -0.1700
Data Index: 8019816 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.6533. Min Act: -0.1700
Data Index: 724049 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.6533. Min Act: -0.1700
Data Index: 3648625 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.6533. Min Act: -0.1700
Data Index: 3870644 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.6533. Min Act: -0.1700
Data Index: 8035054 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.6533. Min Act: -0.1700
Data Index: 1030528 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.5908. Min Act: -0.1700
Data Index: 7750199 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0283. Min Range: -9.0283
Max Act: 8.5908. Min Act: -0.1700
Data Index: 740796 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19