Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3229 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2242. Min Range: -8.2242
Max Act: 8.2242. Min Act: -0.1700
Data Index: 1666785 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2242. Min Range: -8.2242
Max Act: 8.1929. Min Act: -0.1700
Data Index: 6307691 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2242. Min Range: -8.2242
Max Act: 8.0992. Min Act: -0.1700
Data Index: 6794304 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2242. Min Range: -8.2242
Max Act: 8.0054. Min Act: -0.1700
Data Index: 4177475 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.9117. Min Act: -0.1700
Data Index: 3015952 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.7554. Min Act: -0.1700
Data Index: 8007939 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.7554. Min Act: -0.1700
Data Index: 1654694 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.6929. Min Act: -0.1700
Data Index: 7054227 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.6304. Min Act: -0.1700
Data Index: 6876515 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.6304. Min Act: -0.1700
Data Index: 7836841 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.5679. Min Act: -0.1700
Data Index: 3521407 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.5367. Min Act: -0.1700
Data Index: 6828116 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.5054. Min Act: -0.1700
Data Index: 4239858 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.4742. Min Act: -0.1700
Data Index: 287070 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.4117. Min Act: -0.1700
Data Index: 488118 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.3804. Min Act: -0.1700
Data Index: 3920326 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.3804. Min Act: -0.1700
Data Index: 6944683 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.3804. Min Act: -0.1700
Data Index: 4034450 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.3492. Min Act: -0.1700
Data Index: 3902387 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2242. Min Range: -8.2242
Max Act: 7.3492. Min Act: -0.1700
Data Index: 2145358 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19