Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0242. Min Range: -8.0242
Max Act: 8.0242. Min Act: -0.1700
Data Index: 5278334 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.9617. Min Act: -0.1700
Data Index: 3098224 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.8992. Min Act: -0.1700
Data Index: 5629332 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.8367. Min Act: -0.1700
Data Index: 3537245 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.7117. Min Act: -0.1700
Data Index: 5296745 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.7117. Min Act: -0.1700
Data Index: 8757959 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.6492. Min Act: -0.1700
Data Index: 5296743 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.6492. Min Act: -0.1700
Data Index: 8351434 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 2406815 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 5879933 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.6492. Min Act: -0.1700
Data Index: 4644693 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.6492. Min Act: -0.1700
Data Index: 1343618 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 4976778 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 6672265 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 3959015 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 4732014 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 3542961 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 1343617 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 1997418 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0242. Min Range: -8.0242
Max Act: 7.5867. Min Act: -0.1700
Data Index: 7071423 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19