Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2063. Min Range: -7.2063
Max Act: 7.2063. Min Act: -0.1700
Data Index: 3897299 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2063. Min Range: -7.2063
Max Act: 7.2063. Min Act: -0.1700
Data Index: 1804437 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2063. Min Range: -7.2063
Max Act: 7.1438. Min Act: -0.1700
Data Index: 3000585 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2063. Min Range: -7.2063
Max Act: 7.0500. Min Act: -0.1700
Data Index: 3039374 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2063. Min Range: -7.2063
Max Act: 7.0188. Min Act: -0.1700
Data Index: 486659 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.9875. Min Act: -0.1700
Data Index: 6261189 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.9875. Min Act: -0.1700
Data Index: 1951204 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.9563. Min Act: -0.1700
Data Index: 6963334 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.9250. Min Act: -0.1700
Data Index: 1515077 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.9563. Min Act: -0.1700
Data Index: 8623855 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.8938. Min Act: -0.1700
Data Index: 7753366 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.8938. Min Act: -0.1700
Data Index: 6418931 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.8313. Min Act: -0.1700
Data Index: 6513613 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.8313. Min Act: -0.1700
Data Index: 7558031 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.8625. Min Act: -0.1700
Data Index: 5940300 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.8313. Min Act: -0.1700
Data Index: 8474271 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.8000. Min Act: -0.1700
Data Index: 8131785 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.7688. Min Act: -0.1700
Data Index: 5438333 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.7375. Min Act: -0.1700
Data Index: 4781337 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2063. Min Range: -7.2063
Max Act: 6.7375. Min Act: -0.1700
Data Index: 5923384 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19