Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1928 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.5979. Min Act: -0.1700
Data Index: 7784449 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.2229. Min Act: -0.1700
Data Index: 3207242 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.1916. Min Act: -0.1700
Data Index: 6552326 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.1604. Min Act: -0.1700
Data Index: 4366857 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.1291. Min Act: -0.1700
Data Index: 4003376 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.0979. Min Act: -0.1700
Data Index: 42855 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.0666. Min Act: -0.1700
Data Index: 5471827 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.0979. Min Act: -0.1700
Data Index: 4679449 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.0979. Min Act: -0.1700
Data Index: 1541220 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.0979. Min Act: -0.1700
Data Index: 3131347 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.0666. Min Act: -0.1700
Data Index: 8617840 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.0666. Min Act: -0.1700
Data Index: 6167099 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.0666. Min Act: -0.1700
Data Index: 4378341 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.0666. Min Act: -0.1700
Data Index: 3508660 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5979. Min Range: -7.5979
Max Act: 7.0041. Min Act: -0.1700
Data Index: 1387572 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5979. Min Range: -7.5979
Max Act: 6.9729. Min Act: -0.1700
Data Index: 705944 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5979. Min Range: -7.5979
Max Act: 6.9729. Min Act: -0.1700
Data Index: 1970383 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5979. Min Range: -7.5979
Max Act: 6.9104. Min Act: -0.1700
Data Index: 7555672 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5979. Min Range: -7.5979
Max Act: 6.9729. Min Act: -0.1700
Data Index: 2069596 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5979. Min Range: -7.5979
Max Act: 6.9104. Min Act: -0.1700
Data Index: 5247850 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19