Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2222. Min Range: -6.2222
Max Act: 6.2222. Min Act: -0.1700
Data Index: 3610041 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2222. Min Range: -6.2222
Max Act: 6.0972. Min Act: -0.1700
Data Index: 6893869 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2222. Min Range: -6.2222
Max Act: 6.1284. Min Act: -0.1700
Data Index: 5186575 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2222. Min Range: -6.2222
Max Act: 6.0659. Min Act: -0.1700
Data Index: 7386333 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.8784. Min Act: -0.1700
Data Index: 5945949 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.9097. Min Act: -0.1700
Data Index: 8036508 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.8472. Min Act: -0.1700
Data Index: 7757506 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.8159. Min Act: -0.1700
Data Index: 8085530 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.8159. Min Act: -0.1700
Data Index: 5808085 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.7847. Min Act: -0.1700
Data Index: 5312947 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.7847. Min Act: -0.1700
Data Index: 2591697 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.7534. Min Act: -0.1700
Data Index: 6547532 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.7534. Min Act: -0.1700
Data Index: 3980154 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.7534. Min Act: -0.1700
Data Index: 6003972 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.7222. Min Act: -0.1700
Data Index: 4553637 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.6909. Min Act: -0.1700
Data Index: 4222825 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.6909. Min Act: -0.1700
Data Index: 3611037 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.7222. Min Act: -0.1700
Data Index: 6049842 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.6597. Min Act: -0.1700
Data Index: 3785135 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2222. Min Range: -6.2222
Max Act: 5.6597. Min Act: -0.1700
Data Index: 110391 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19