Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.3232. Min Act: -0.1700
Data Index: 3096688 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.2919. Min Act: -0.1700
Data Index: 932757 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.2294. Min Act: -0.1700
Data Index: 3977681 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.2294. Min Act: -0.1700
Data Index: 4408633 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.2294. Min Act: -0.1700
Data Index: 1712266 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.2294. Min Act: -0.1700
Data Index: 351514 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.2294. Min Act: -0.1700
Data Index: 3565298 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1669. Min Act: -0.1700
Data Index: 4433718 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1669. Min Act: -0.1700
Data Index: 6657046 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1669. Min Act: -0.1700
Data Index: 5696012 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1669. Min Act: -0.1700
Data Index: 644411 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1669. Min Act: -0.1700
Data Index: 7222971 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1669. Min Act: -0.1700
Data Index: 8377694 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1357. Min Act: -0.1700
Data Index: 1904051 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1357. Min Act: -0.1700
Data Index: 4971815 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1357. Min Act: -0.1700
Data Index: 6219691 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1357. Min Act: -0.1700
Data Index: 8264368 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1044. Min Act: -0.1700
Data Index: 2531883 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.0732. Min Act: -0.1700
Data Index: 58083 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3232. Min Range: -5.3232
Max Act: 5.1044. Min Act: -0.1700
Data Index: 141153 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19