Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3330 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3817. Min Act: -0.1700
Data Index: 2827773 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3504. Min Act: -0.1700
Data Index: 7800988 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 7285891 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 7403441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 1924451 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2879. Min Act: -0.1700
Data Index: 5516428 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2567. Min Act: -0.1700
Data Index: 4523900 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2567. Min Act: -0.1700
Data Index: 2648499 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2567. Min Act: -0.1700
Data Index: 1236396 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2567. Min Act: -0.1700
Data Index: 3758399 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 2131493 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 4385318 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 5117589 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 1136575 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 5459524 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 2641812 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 2017230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.1942. Min Act: -0.1700
Data Index: 4035226 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 6312071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 6357769 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19