Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1190 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.8539. Min Act: -0.1700
Data Index: 1665858 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.8226. Min Act: -0.1700
Data Index: 4979999 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.7914. Min Act: -0.1700
Data Index: 242058 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.7601. Min Act: -0.1700
Data Index: 242059 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.7914. Min Act: -0.1700
Data Index: 1993117 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.6664. Min Act: -0.1700
Data Index: 8461184 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.6039. Min Act: -0.1700
Data Index: 8262874 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.5726. Min Act: -0.1700
Data Index: 3770913 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.6039. Min Act: -0.1700
Data Index: 4761111 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.5726. Min Act: -0.1700
Data Index: 5168177 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.5726. Min Act: -0.1700
Data Index: 8015337 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.5726. Min Act: -0.1700
Data Index: 7920404 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.5726. Min Act: -0.1700
Data Index: 799384 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.5414. Min Act: -0.1700
Data Index: 8684848 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.5414. Min Act: -0.1700
Data Index: 5396813 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.5101. Min Act: -0.1700
Data Index: 2257695 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.4789. Min Act: -0.1700
Data Index: 4946504 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.5101. Min Act: -0.1700
Data Index: 5806354 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.5101. Min Act: -0.1700
Data Index: 1712776 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8539. Min Range: -5.8539
Max Act: 5.4789. Min Act: -0.1700
Data Index: 357955 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19