Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2135. Min Range: -12.2135
Max Act: 12.2135. Min Act: -0.1700
Data Index: 7133271 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2135. Min Range: -12.2135
Max Act: 11.9635. Min Act: -0.1700
Data Index: 3459442 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2135. Min Range: -12.2135
Max Act: 11.7760. Min Act: -0.1700
Data Index: 7133262 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2135. Min Range: -12.2135
Max Act: 11.2760. Min Act: -0.1700
Data Index: 2579746 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2135. Min Range: -12.2135
Max Act: 11.2135. Min Act: -0.1700
Data Index: 2858524 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2135. Min Range: -12.2135
Max Act: 11.0260. Min Act: -0.1700
Data Index: 3103943 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2135. Min Range: -12.2135
Max Act: 11.0260. Min Act: -0.1700
Data Index: 3706346 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.9635. Min Act: -0.1700
Data Index: 81956 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.9635. Min Act: -0.1700
Data Index: 4919633 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.9010. Min Act: -0.1700
Data Index: 1288062 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.9010. Min Act: -0.1700
Data Index: 5584260 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.8385. Min Act: -0.1700
Data Index: 3931 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.8385. Min Act: -0.1700
Data Index: 1625681 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.7760. Min Act: -0.1700
Data Index: 4919632 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.7760. Min Act: -0.1700
Data Index: 6599007 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.7760. Min Act: -0.1700
Data Index: 4520292 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.7760. Min Act: -0.1700
Data Index: 2656657 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.7760. Min Act: -0.1700
Data Index: 4371687 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.7760. Min Act: -0.1700
Data Index: 4365127 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2135. Min Range: -12.2135
Max Act: 10.7135. Min Act: -0.1700
Data Index: 714752 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19