Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2098 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.2534. Min Act: -0.1700
Data Index: 66129 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.1597. Min Act: -0.1700
Data Index: 2818229 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0972. Min Act: -0.1700
Data Index: 8077107 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0659. Min Act: -0.1700
Data Index: 5132050 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0659. Min Act: -0.1700
Data Index: 3779577 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0347. Min Act: -0.1700
Data Index: 8119793 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0034. Min Act: -0.1700
Data Index: 1966811 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0034. Min Act: -0.1700
Data Index: 4755942 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.9722. Min Act: -0.1700
Data Index: 2531232 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.9722. Min Act: -0.1700
Data Index: 5886172 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.9722. Min Act: -0.1700
Data Index: 2034660 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.9409. Min Act: -0.1700
Data Index: 5497781 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.9097. Min Act: -0.1700
Data Index: 6800526 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.9409. Min Act: -0.1700
Data Index: 5276372 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.9097. Min Act: -0.1700
Data Index: 3788049 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.9097. Min Act: -0.1700
Data Index: 3705154 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.8784. Min Act: -0.1700
Data Index: 1882172 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.8784. Min Act: -0.1700
Data Index: 7481498 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.8784. Min Act: -0.1700
Data Index: 2861491 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2534. Min Range: -6.2534
Max Act: 5.8784. Min Act: -0.1700
Data Index: 2820361 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19