Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8118. Min Range: -9.8118
Max Act: 9.8118. Min Act: -0.1700
Data Index: 55547 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8118. Min Range: -9.8118
Max Act: 9.4368. Min Act: -0.1700
Data Index: 931041 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8118. Min Range: -9.8118
Max Act: 9.2493. Min Act: -0.1700
Data Index: 1276944 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.8743. Min Act: -0.1700
Data Index: 7832776 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.8743. Min Act: -0.1700
Data Index: 4273714 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.8118. Min Act: -0.1700
Data Index: 4678949 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.8118. Min Act: -0.1700
Data Index: 2180871 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.8743. Min Act: -0.1700
Data Index: 3205829 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.8118. Min Act: -0.1700
Data Index: 5375366 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.8118. Min Act: -0.1700
Data Index: 2906865 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.7493. Min Act: -0.1700
Data Index: 1276949 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.6868. Min Act: -0.1700
Data Index: 3123130 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.6243. Min Act: -0.1700
Data Index: 7552357 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.6868. Min Act: -0.1700
Data Index: 891838 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.6243. Min Act: -0.1700
Data Index: 4462488 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.5618. Min Act: -0.1700
Data Index: 7506652 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.4993. Min Act: -0.1700
Data Index: 1276942 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.4993. Min Act: -0.1700
Data Index: 7599883 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.4993. Min Act: -0.1700
Data Index: 6377599 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8118. Min Range: -9.8118
Max Act: 8.5618. Min Act: -0.1700
Data Index: 3396370 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19