Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3904 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.7942. Min Act: -0.1700
Data Index: 3157702 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.7004. Min Act: -0.1700
Data Index: 1207976 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.6379. Min Act: -0.1700
Data Index: 2212041 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.5442. Min Act: -0.1700
Data Index: 135524 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.5442. Min Act: -0.1700
Data Index: 1026074 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.4817. Min Act: -0.1700
Data Index: 5944729 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.4817. Min Act: -0.1700
Data Index: 6482674 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.4504. Min Act: -0.1700
Data Index: 7718489 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.4192. Min Act: -0.1700
Data Index: 797147 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.4192. Min Act: -0.1700
Data Index: 2764418 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.3879. Min Act: -0.1700
Data Index: 1562907 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.3879. Min Act: -0.1700
Data Index: 58659 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.3254. Min Act: -0.1700
Data Index: 3157709 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.3254. Min Act: -0.1700
Data Index: 5932147 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.3254. Min Act: -0.1700
Data Index: 5267676 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.3254. Min Act: -0.1700
Data Index: 5297703 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.2942. Min Act: -0.1700
Data Index: 2106455 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.3254. Min Act: -0.1700
Data Index: 5678960 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.2942. Min Act: -0.1700
Data Index: 416160 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7942. Min Range: -6.7942
Max Act: 6.2942. Min Act: -0.1700
Data Index: 4625473 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19