Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1505 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0196. Min Range: -6.0196
Max Act: 6.0196. Min Act: -0.1700
Data Index: 5543617 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.9884. Min Act: -0.1700
Data Index: 3853219 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.9571. Min Act: -0.1700
Data Index: 770170 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.9571. Min Act: -0.1700
Data Index: 7917229 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.9259. Min Act: -0.1700
Data Index: 8736133 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.8946. Min Act: -0.1700
Data Index: 919761 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.8634. Min Act: -0.1700
Data Index: 1423942 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.8634. Min Act: -0.1700
Data Index: 5543615 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.8946. Min Act: -0.1700
Data Index: 2080479 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.8634. Min Act: -0.1700
Data Index: 7309851 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.8634. Min Act: -0.1700
Data Index: 837254 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.8634. Min Act: -0.1700
Data Index: 2165170 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7696. Min Act: -0.1700
Data Index: 2892525 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7384. Min Act: -0.1700
Data Index: 8141649 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7384. Min Act: -0.1700
Data Index: 1409807 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7696. Min Act: -0.1700
Data Index: 7719879 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7696. Min Act: -0.1700
Data Index: 6282232 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7696. Min Act: -0.1700
Data Index: 1593582 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7384. Min Act: -0.1700
Data Index: 2405833 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3323010 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19