Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0234. Min Range: -6.0234
Max Act: 6.0234. Min Act: -0.1700
Data Index: 3079911 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.8672. Min Act: -0.1700
Data Index: 7176067 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.6484. Min Act: -0.1700
Data Index: 6520936 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.6172. Min Act: -0.1700
Data Index: 1834104 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.6172. Min Act: -0.1700
Data Index: 8602134 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.5859. Min Act: -0.1700
Data Index: 2416299 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.5547. Min Act: -0.1700
Data Index: 8671912 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.5234. Min Act: -0.1700
Data Index: 6037965 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.5234. Min Act: -0.1700
Data Index: 5418310 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4609. Min Act: -0.1700
Data Index: 2972063 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4922. Min Act: -0.1700
Data Index: 5596599 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4609. Min Act: -0.1700
Data Index: 7650805 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4609. Min Act: -0.1700
Data Index: 5905062 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4922. Min Act: -0.1700
Data Index: 2422426 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4922. Min Act: -0.1700
Data Index: 1715052 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4609. Min Act: -0.1700
Data Index: 6011612 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4609. Min Act: -0.1700
Data Index: 3708449 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4297. Min Act: -0.1700
Data Index: 6604223 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4297. Min Act: -0.1700
Data Index: 755037 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0234. Min Range: -6.0234
Max Act: 5.4297. Min Act: -0.1700
Data Index: 8571194 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19