Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3947 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.9551. Min Act: -0.1700
Data Index: 916424 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.8926. Min Act: -0.1700
Data Index: 3679296 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.8926. Min Act: -0.1700
Data Index: 8238832 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.8926. Min Act: -0.1700
Data Index: 2648378 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.8926. Min Act: -0.1700
Data Index: 1990779 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.7988. Min Act: -0.1700
Data Index: 3728144 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.8300. Min Act: -0.1700
Data Index: 7474067 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.7988. Min Act: -0.1700
Data Index: 7896878 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.8300. Min Act: -0.1700
Data Index: 8559876 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.8300. Min Act: -0.1700
Data Index: 8596435 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.7988. Min Act: -0.1700
Data Index: 6608336 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.8300. Min Act: -0.1700
Data Index: 6578367 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.8300. Min Act: -0.1700
Data Index: 4871649 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.8300. Min Act: -0.1700
Data Index: 1478293 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.7988. Min Act: -0.1700
Data Index: 3163617 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.7988. Min Act: -0.1700
Data Index: 3119644 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.7988. Min Act: -0.1700
Data Index: 399516 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.7675. Min Act: -0.1700
Data Index: 5736220 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.7988. Min Act: -0.1700
Data Index: 4421443 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9551. Min Range: -3.9551
Max Act: 3.7988. Min Act: -0.1700
Data Index: 2303466 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19