Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.7562. Min Act: -0.1700
Data Index: 2314554 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.6624. Min Act: -0.1700
Data Index: 428914 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.5528. Min Act: -0.1700
Data Index: 2772443 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.5215. Min Act: -0.1700
Data Index: 4832758 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.5215. Min Act: -0.1700
Data Index: 4495041 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4902. Min Act: -0.1700
Data Index: 939945 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.5058. Min Act: -0.1700
Data Index: 5361808 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.5058. Min Act: -0.1700
Data Index: 8070163 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4902. Min Act: -0.1700
Data Index: 7910939 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4745. Min Act: -0.1700
Data Index: 7829649 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4745. Min Act: -0.1700
Data Index: 1819548 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4588. Min Act: -0.1700
Data Index: 1540050 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4588. Min Act: -0.1700
Data Index: 3248943 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4275. Min Act: -0.1700
Data Index: 3788942 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4118. Min Act: -0.1700
Data Index: 7263927 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4118. Min Act: -0.1700
Data Index: 1491780 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4118. Min Act: -0.1700
Data Index: 159545 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4118. Min Act: -0.1700
Data Index: 177213 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.4118. Min Act: -0.1700
Data Index: 8623456 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7562. Min Range: -3.7562
Max Act: 3.3805. Min Act: -0.1700
Data Index: 7533434 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19