Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 168 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.7219. Min Act: -0.1700
Data Index: 1247889 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.5344. Min Act: -0.1700
Data Index: 40252 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.5032. Min Act: -0.1700
Data Index: 7784 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.4719. Min Act: -0.1700
Data Index: 4726153 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.4407. Min Act: -0.1700
Data Index: 2485688 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.4719. Min Act: -0.1700
Data Index: 1817929 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.4719. Min Act: -0.1700
Data Index: 384673 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.4407. Min Act: -0.1700
Data Index: 6880060 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.4094. Min Act: -0.1700
Data Index: 677534 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3782. Min Act: -0.1700
Data Index: 317080 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3782. Min Act: -0.1700
Data Index: 6729211 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3782. Min Act: -0.1700
Data Index: 7265670 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3469. Min Act: -0.1700
Data Index: 4581003 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3469. Min Act: -0.1700
Data Index: 5569406 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3157. Min Act: -0.1700
Data Index: 2498737 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3469. Min Act: -0.1700
Data Index: 1059056 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3157. Min Act: -0.1700
Data Index: 4284734 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3157. Min Act: -0.1700
Data Index: 3860099 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3469. Min Act: -0.1700
Data Index: 2464700 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7219. Min Range: -6.7219
Max Act: 6.3157. Min Act: -0.1700
Data Index: 5036044 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19