Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1551. Min Range: -6.1551
Max Act: 6.1551. Min Act: -0.1700
Data Index: 6672208 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1551. Min Range: -6.1551
Max Act: 6.1239. Min Act: -0.1700
Data Index: 6417419 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1551. Min Range: -6.1551
Max Act: 6.0926. Min Act: -0.1700
Data Index: 587691 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1551. Min Range: -6.1551
Max Act: 6.0301. Min Act: -0.1700
Data Index: 7932496 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8739. Min Act: -0.1700
Data Index: 8322524 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8739. Min Act: -0.1700
Data Index: 3767072 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8426. Min Act: -0.1700
Data Index: 5551078 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8114. Min Act: -0.1700
Data Index: 6549008 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8114. Min Act: -0.1700
Data Index: 33113 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7176. Min Act: -0.1700
Data Index: 1220211 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7176. Min Act: -0.1700
Data Index: 917616 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7176. Min Act: -0.1697
Data Index: 146484 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7176. Min Act: -0.1700
Data Index: 840611 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7176. Min Act: -0.1700
Data Index: 5539464 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6864. Min Act: -0.1700
Data Index: 5496389 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6864. Min Act: -0.1700
Data Index: 3257055 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7176. Min Act: -0.1700
Data Index: 4584148 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6864. Min Act: -0.1700
Data Index: 1011199 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 2152536 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6864. Min Act: -0.1700
Data Index: 774382 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19