Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 203 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0399. Min Range: -7.0399
Max Act: 7.0399. Min Act: -0.1700
Data Index: 7737493 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.8524. Min Act: -0.1700
Data Index: 8500235 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.7899. Min Act: -0.1700
Data Index: 8675241 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.7274. Min Act: -0.1700
Data Index: 1635406 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6962. Min Act: -0.1700
Data Index: 5892090 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6649. Min Act: -0.1700
Data Index: 1317651 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6337. Min Act: -0.1700
Data Index: 6086266 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6337. Min Act: -0.1700
Data Index: 8675242 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6024. Min Act: -0.1700
Data Index: 4112867 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5712. Min Act: -0.1700
Data Index: 8172980 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5712. Min Act: -0.1700
Data Index: 2008556 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5399. Min Act: -0.1700
Data Index: 7701576 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5399. Min Act: -0.1700
Data Index: 2752829 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5399. Min Act: -0.1700
Data Index: 8170988 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5087. Min Act: -0.1700
Data Index: 543957 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5087. Min Act: -0.1700
Data Index: 1374655 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.4462. Min Act: -0.1700
Data Index: 1417488 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.4462. Min Act: -0.1700
Data Index: 292605 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.4149. Min Act: -0.1700
Data Index: 5530019 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.4149. Min Act: -0.1700
Data Index: 1389878 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19