Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.9623. Min Act: -0.1700
Data Index: 1926899 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.9623. Min Act: -0.1700
Data Index: 6409817 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.9311. Min Act: -0.1700
Data Index: 7894709 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.8373. Min Act: -0.1700
Data Index: 8593334 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.8061. Min Act: -0.1700
Data Index: 3754733 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.7748. Min Act: -0.1700
Data Index: 5455741 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.7436. Min Act: -0.1700
Data Index: 2179409 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.7436. Min Act: -0.1700
Data Index: 5456128 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.7123. Min Act: -0.1700
Data Index: 4203718 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.7123. Min Act: -0.1700
Data Index: 436162 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.7123. Min Act: -0.1700
Data Index: 4112012 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.6811. Min Act: -0.1700
Data Index: 4120680 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.6811. Min Act: -0.1700
Data Index: 2740070 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.6811. Min Act: -0.1700
Data Index: 6276641 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.6811. Min Act: -0.1700
Data Index: 3916984 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.6811. Min Act: -0.1700
Data Index: 2202931 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.6811. Min Act: -0.1700
Data Index: 6112434 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.6811. Min Act: -0.1700
Data Index: 7584086 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.6811. Min Act: -0.1700
Data Index: 7344885 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.6498. Min Act: -0.1700
Data Index: 4636267 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19