Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1919 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1708. Min Range: -6.1708
Max Act: 6.1708. Min Act: -0.1699
Data Index: 1570688 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1708. Min Range: -6.1708
Max Act: 6.1083. Min Act: -0.1700
Data Index: 7493526 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1708. Min Range: -6.1708
Max Act: 6.0771. Min Act: -0.1700
Data Index: 2221033 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1708. Min Range: -6.1708
Max Act: 6.0458. Min Act: -0.1700
Data Index: 3093173 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1708. Min Range: -6.1708
Max Act: 6.0458. Min Act: -0.1700
Data Index: 3509961 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1708. Min Range: -6.1708
Max Act: 6.0146. Min Act: -0.1700
Data Index: 8635828 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1708. Min Range: -6.1708
Max Act: 6.0146. Min Act: -0.1700
Data Index: 7153849 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9521. Min Act: -0.1700
Data Index: 4960197 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9521. Min Act: -0.1700
Data Index: 1901879 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9521. Min Act: -0.1700
Data Index: 5544583 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9521. Min Act: -0.1700
Data Index: 6860176 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9521. Min Act: -0.1700
Data Index: 7918840 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9208. Min Act: -0.1700
Data Index: 208742 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9208. Min Act: -0.1700
Data Index: 527648 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9208. Min Act: -0.1700
Data Index: 5555890 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.8896. Min Act: -0.1700
Data Index: 7770804 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9208. Min Act: -0.1700
Data Index: 5646651 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9208. Min Act: -0.1700
Data Index: 437707 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9208. Min Act: -0.1700
Data Index: 7996946 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1708. Min Range: -6.1708
Max Act: 5.9208. Min Act: -0.1700
Data Index: 4633067 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19