Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4191 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.8555. Min Act: -0.1700
Data Index: 1993503 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.8555. Min Act: -0.1700
Data Index: 7011062 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.8243. Min Act: -0.1700
Data Index: 7949569 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.6680. Min Act: -0.1700
Data Index: 792366 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.6368. Min Act: -0.1700
Data Index: 665365 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.5743. Min Act: -0.1700
Data Index: 1533440 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4805. Min Act: -0.1700
Data Index: 2671483 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4493. Min Act: -0.1700
Data Index: 8414838 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4805. Min Act: -0.1700
Data Index: 3147138 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4805. Min Act: -0.1700
Data Index: 4425083 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4493. Min Act: -0.1700
Data Index: 6565305 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4805. Min Act: -0.1700
Data Index: 5826398 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4493. Min Act: -0.1700
Data Index: 4649227 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4493. Min Act: -0.1700
Data Index: 3250694 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4180. Min Act: -0.1700
Data Index: 4636883 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4180. Min Act: -0.1700
Data Index: 4078612 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.4180. Min Act: -0.1700
Data Index: 5542967 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.3868. Min Act: -0.1700
Data Index: 8432389 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.3555. Min Act: -0.1700
Data Index: 138628 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8555. Min Range: -4.8555
Max Act: 4.3868. Min Act: -0.1700
Data Index: 7766512 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19