Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6125 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1243. Min Range: -6.1243
Max Act: 6.1243. Min Act: -0.1700
Data Index: 4309064 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1243. Min Range: -6.1243
Max Act: 6.1243. Min Act: -0.1700
Data Index: 3995961 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1243. Min Range: -6.1243
Max Act: 6.1243. Min Act: -0.1700
Data Index: 2793943 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.9993. Min Act: -0.1700
Data Index: 130818 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.9368. Min Act: -0.1700
Data Index: 4857877 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.9055. Min Act: -0.1700
Data Index: 5387257 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.9055. Min Act: -0.1700
Data Index: 3410321 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.9055. Min Act: -0.1700
Data Index: 699645 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.8743. Min Act: -0.1700
Data Index: 2963624 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.8743. Min Act: -0.1700
Data Index: 8756433 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.8743. Min Act: -0.1700
Data Index: 452749 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.8430. Min Act: -0.1700
Data Index: 3448665 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.8430. Min Act: -0.1700
Data Index: 3824689 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.8118. Min Act: -0.1700
Data Index: 2399980 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.8118. Min Act: -0.1700
Data Index: 5340171 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.8118. Min Act: -0.1700
Data Index: 1266205 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.8118. Min Act: -0.1700
Data Index: 6110803 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.8118. Min Act: -0.1700
Data Index: 1064778 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.7493. Min Act: -0.1700
Data Index: 3142934 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1243. Min Range: -6.1243
Max Act: 5.7805. Min Act: -0.1700
Data Index: 6001649 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19