Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.9623. Min Act: -0.1700
Data Index: 83366 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.7123. Min Act: -0.1700
Data Index: 3907989 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.4623. Min Act: -0.1700
Data Index: 3491262 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.4936. Min Act: -0.1700
Data Index: 5639353 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.4311. Min Act: -0.1700
Data Index: 2727500 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.3998. Min Act: -0.1700
Data Index: 2598989 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.3373. Min Act: -0.1700
Data Index: 3803068 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.2748. Min Act: -0.1700
Data Index: 6332577 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.2748. Min Act: -0.1700
Data Index: 8719048 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.2436. Min Act: -0.1700
Data Index: 6089917 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.2123. Min Act: -0.1700
Data Index: 8695692 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.2748. Min Act: -0.1700
Data Index: 122442 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.2436. Min Act: -0.1700
Data Index: 5139000 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.1811. Min Act: -0.1700
Data Index: 7946139 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.1811. Min Act: -0.1700
Data Index: 201193 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.1498. Min Act: -0.1700
Data Index: 3911343 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.1186. Min Act: -0.1700
Data Index: 7295515 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.0873. Min Act: -0.1700
Data Index: 2535477 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.1186. Min Act: -0.1700
Data Index: 3428336 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9623. Min Range: -7.9623
Max Act: 7.1186. Min Act: -0.1700
Data Index: 4263353 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19