Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1366 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3196. Min Act: -0.1700
Data Index: 3961047 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3039. Min Act: -0.1700
Data Index: 7870251 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 5033127 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 4928971 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 7949550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 256854 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 2972298 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2725. Min Act: -0.1700
Data Index: 3425504 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2725. Min Act: -0.1700
Data Index: 3030741 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2725. Min Act: -0.1700
Data Index: 6436855 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 2250514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 7867028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 2131071 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 7677859 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 338536 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 4255359 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 7539430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 5045160 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2254. Min Act: -0.1700
Data Index: 1281926 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2254. Min Act: -0.1700
Data Index: 4860224 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19