Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3944 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.7450. Min Act: -0.1700
Data Index: 3787911 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.7450. Min Act: -0.1700
Data Index: 6847943 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6825. Min Act: -0.1700
Data Index: 2467566 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6825. Min Act: -0.1700
Data Index: 4728150 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6825. Min Act: -0.1700
Data Index: 4429303 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6825. Min Act: -0.1700
Data Index: 627937 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6825. Min Act: -0.1700
Data Index: 5698904 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6825. Min Act: -0.1700
Data Index: 1363496 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6513. Min Act: -0.1700
Data Index: 7097823 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6200. Min Act: -0.1700
Data Index: 7926372 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6200. Min Act: -0.1700
Data Index: 1127033 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6200. Min Act: -0.1700
Data Index: 7972231 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.6200. Min Act: -0.1700
Data Index: 2663840 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.5888. Min Act: -0.1700
Data Index: 613633 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.5888. Min Act: -0.1700
Data Index: 472763 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.5888. Min Act: -0.1700
Data Index: 7097817 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.5888. Min Act: -0.1700
Data Index: 181409 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.5888. Min Act: -0.1700
Data Index: 1274285 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.5575. Min Act: -0.1700
Data Index: 4728151 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7450. Min Range: -4.7450
Max Act: 4.5575. Min Act: -0.1700
Data Index: 7184863 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19