Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2467 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.9306. Min Act: -0.1700
Data Index: 8344041 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8671. Min Act: -0.1700
Data Index: 7155964 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8512. Min Act: -0.1700
Data Index: 3491754 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8194. Min Act: -0.1700
Data Index: 3491755 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8353. Min Act: -0.1700
Data Index: 6285641 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8353. Min Act: -0.1700
Data Index: 5910575 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8353. Min Act: -0.1700
Data Index: 3188626 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8353. Min Act: -0.1700
Data Index: 3131895 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8353. Min Act: -0.1700
Data Index: 2115646 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8194. Min Act: -0.1700
Data Index: 2058966 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8194. Min Act: -0.1700
Data Index: 7081903 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8194. Min Act: -0.1700
Data Index: 6155793 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8194. Min Act: -0.1700
Data Index: 1391241 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8194. Min Act: -0.1700
Data Index: 5020280 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8194. Min Act: -0.1700
Data Index: 6559760 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8035. Min Act: -0.1700
Data Index: 5882947 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8035. Min Act: -0.1700
Data Index: 3491761 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8035. Min Act: -0.1700
Data Index: 104778 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7876. Min Act: -0.1700
Data Index: 3212550 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7876. Min Act: -0.1700
Data Index: 3375657 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19