Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 101 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8767. Min Range: -9.8767
Max Act: 9.8767. Min Act: -0.1700
Data Index: 7064976 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8767. Min Range: -9.8767
Max Act: 9.1267. Min Act: -0.1700
Data Index: 7255653 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8767. Min Range: -9.8767
Max Act: 9.0642. Min Act: -0.1700
Data Index: 633977 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8767. Min Range: -9.8767
Max Act: 9.0017. Min Act: -0.1700
Data Index: 7284331 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8767. Min Range: -9.8767
Max Act: 9.0017. Min Act: -0.1700
Data Index: 3743122 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.9392. Min Act: -0.1700
Data Index: 6403721 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.9392. Min Act: -0.1700
Data Index: 4760980 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.8767. Min Act: -0.1700
Data Index: 8326747 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.8767. Min Act: -0.1700
Data Index: 6662442 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.8767. Min Act: -0.1700
Data Index: 1016457 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.8142. Min Act: -0.1700
Data Index: 361857 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.7517. Min Act: -0.1699
Data Index: 2947794 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.8142. Min Act: -0.1700
Data Index: 7618485 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.7517. Min Act: -0.1697
Data Index: 8218898 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.7517. Min Act: -0.1700
Data Index: 1339905 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.7517. Min Act: -0.1700
Data Index: 4015181 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.6892. Min Act: -0.1700
Data Index: 2169462 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.6892. Min Act: -0.1676
Data Index: 5534337 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.7517. Min Act: -0.1700
Data Index: 6067628 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8767. Min Range: -9.8767
Max Act: 8.6892. Min Act: -0.1700
Data Index: 1093145 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19