Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4301 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.4990. Min Act: -0.1700
Data Index: 3511531 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.4365. Min Act: -0.1700
Data Index: 4570052 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.3428. Min Act: -0.1700
Data Index: 3801053 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.3428. Min Act: -0.1700
Data Index: 7036668 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.0928. Min Act: -0.1700
Data Index: 6248340 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.0303. Min Act: -0.1700
Data Index: 2930794 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.0303. Min Act: -0.1700
Data Index: 3376096 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4990. Min Range: -6.4990
Max Act: 6.0303. Min Act: -0.1700
Data Index: 6161202 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.9678. Min Act: -0.1700
Data Index: 5270810 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.9990. Min Act: -0.1700
Data Index: 6233397 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.9053. Min Act: -0.1700
Data Index: 6757553 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.8740. Min Act: -0.1700
Data Index: 10090 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.8428. Min Act: -0.1700
Data Index: 5931157 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.8115. Min Act: -0.1700
Data Index: 3523239 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.7803. Min Act: -0.1700
Data Index: 17533 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.7803. Min Act: -0.1700
Data Index: 6324567 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.6865. Min Act: -0.1700
Data Index: 6192481 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.6240. Min Act: -0.1700
Data Index: 6047669 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.6240. Min Act: -0.1700
Data Index: 1962405 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4990. Min Range: -6.4990
Max Act: 5.6240. Min Act: -0.1700
Data Index: 3263718 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19