Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 120 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1618. Min Range: -5.1618
Max Act: 5.1618. Min Act: -0.1700
Data Index: 3015388 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1618. Min Range: -5.1618
Max Act: 5.1618. Min Act: -0.1700
Data Index: 3534760 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1618. Min Range: -5.1618
Max Act: 5.0055. Min Act: -0.1700
Data Index: 7318887 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.9118. Min Act: -0.1700
Data Index: 3761266 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.8805. Min Act: -0.1700
Data Index: 205558 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.8805. Min Act: -0.1700
Data Index: 5586124 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.8493. Min Act: -0.1700
Data Index: 1532992 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7868. Min Act: -0.1700
Data Index: 1533009 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7555. Min Act: -0.1700
Data Index: 2188066 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7555. Min Act: -0.1700
Data Index: 7130656 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7555. Min Act: -0.1700
Data Index: 6924007 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7243. Min Act: -0.1700
Data Index: 8195058 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7243. Min Act: -0.1700
Data Index: 5397581 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7243. Min Act: -0.1700
Data Index: 830157 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7243. Min Act: -0.1700
Data Index: 5014786 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7243. Min Act: -0.1700
Data Index: 1533011 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7243. Min Act: -0.1700
Data Index: 1059732 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7243. Min Act: -0.1700
Data Index: 3288298 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7243. Min Act: -0.1700
Data Index: 3357376 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1618. Min Range: -5.1618
Max Act: 4.7243. Min Act: -0.1700
Data Index: 4915885 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19