Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5625 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.8641. Min Act: -0.1700
Data Index: 4120271 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.9266. Min Act: -0.1700
Data Index: 430875 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.9266. Min Act: -0.1700
Data Index: 986891 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.8641. Min Act: -0.1700
Data Index: 5429603 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.9266. Min Act: -0.1700
Data Index: 609196 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.7391. Min Act: -0.1700
Data Index: 2230736 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.7391. Min Act: -0.1700
Data Index: 4361328 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.6766. Min Act: -0.1700
Data Index: 2405060 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.6766. Min Act: -0.1700
Data Index: 56051 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.6766. Min Act: -0.1700
Data Index: 4206400 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.6766. Min Act: -0.1700
Data Index: 1531454 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.6766. Min Act: -0.1700
Data Index: 7617475 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.6766. Min Act: -0.1700
Data Index: 8709981 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.6141. Min Act: -0.1700
Data Index: 197159 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.6141. Min Act: -0.1700
Data Index: 2101071 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.6141. Min Act: -0.1700
Data Index: 3109031 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.5516. Min Act: -0.1700
Data Index: 1294659 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.5516. Min Act: -0.1700
Data Index: 3560866 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.5516. Min Act: -0.1700
Data Index: 363193 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9266. Min Range: -8.9266
Max Act: 8.5516. Min Act: -0.1700
Data Index: 4650267 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19