Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3766 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.7676. Min Act: -0.1700
Data Index: 6652558 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.6113. Min Act: -0.1700
Data Index: 2655021 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.6113. Min Act: -0.1700
Data Index: 7283100 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.6113. Min Act: -0.1700
Data Index: 6317209 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.5801. Min Act: -0.1700
Data Index: 6317207 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.5801. Min Act: -0.1700
Data Index: 1885756 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.5488. Min Act: -0.1700
Data Index: 3606024 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.5488. Min Act: -0.1700
Data Index: 3155336 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.4863. Min Act: -0.1700
Data Index: 5547946 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.5176. Min Act: -0.1700
Data Index: 4115779 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.5176. Min Act: -0.1700
Data Index: 4115780 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.5176. Min Act: -0.1700
Data Index: 566756 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.4863. Min Act: -0.1700
Data Index: 7029524 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.4551. Min Act: -0.1700
Data Index: 7510223 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.4551. Min Act: -0.1700
Data Index: 4661583 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.4551. Min Act: -0.1700
Data Index: 6172424 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.4551. Min Act: -0.1700
Data Index: 1942566 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.4551. Min Act: -0.1700
Data Index: 4690629 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.4551. Min Act: -0.1700
Data Index: 343063 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7676. Min Range: -4.7676
Max Act: 4.4238. Min Act: -0.1700
Data Index: 4694719 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19