Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2716 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.8303. Min Act: -0.1700
Data Index: 4256887 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.7678. Min Act: -0.1700
Data Index: 1238162 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.6428. Min Act: -0.1700
Data Index: 8821903 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.7053. Min Act: -0.1700
Data Index: 1478866 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.6428. Min Act: -0.1700
Data Index: 4450493 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.3928. Min Act: -0.1700
Data Index: 7366496 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.3303. Min Act: -0.1700
Data Index: 3332830 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.2678. Min Act: -0.1700
Data Index: 3994819 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.2053. Min Act: -0.1700
Data Index: 4805644 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.1428. Min Act: -0.1700
Data Index: 4281073 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.1428. Min Act: -0.1700
Data Index: 2089944 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.1428. Min Act: -0.1700
Data Index: 6355588 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.0803. Min Act: -0.1700
Data Index: 1896207 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.0178. Min Act: -0.1700
Data Index: 3528548 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.0178. Min Act: -0.1700
Data Index: 3149256 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8303. Min Range: -9.8303
Max Act: 9.0178. Min Act: -0.1700
Data Index: 8775510 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8303. Min Range: -9.8303
Max Act: 8.9553. Min Act: -0.1700
Data Index: 7437462 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8303. Min Range: -9.8303
Max Act: 8.8928. Min Act: -0.1700
Data Index: 5708687 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8303. Min Range: -9.8303
Max Act: 8.8303. Min Act: -0.1700
Data Index: 7973517 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8303. Min Range: -9.8303
Max Act: 8.8928. Min Act: -0.1700
Data Index: 197668 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19