Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1967 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.7986. Min Act: -0.1700
Data Index: 3613134 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.3611. Min Act: -0.1700
Data Index: 7885352 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.3611. Min Act: -0.1700
Data Index: 7722022 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.2986. Min Act: -0.1700
Data Index: 8198741 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.1736. Min Act: -0.1700
Data Index: 5835506 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.2361. Min Act: -0.1700
Data Index: 1077630 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.1736. Min Act: -0.1700
Data Index: 3277895 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.1423. Min Act: -0.1700
Data Index: 3434 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.0798. Min Act: -0.1700
Data Index: 4882301 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.0486. Min Act: -0.1700
Data Index: 8549520 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7986. Min Range: -8.7986
Max Act: 8.0173. Min Act: -0.1700
Data Index: 7894023 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7986. Min Range: -8.7986
Max Act: 7.9861. Min Act: -0.1700
Data Index: 2667141 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7986. Min Range: -8.7986
Max Act: 7.9548. Min Act: -0.1700
Data Index: 4504938 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7986. Min Range: -8.7986
Max Act: 7.9548. Min Act: -0.1700
Data Index: 2230583 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7986. Min Range: -8.7986
Max Act: 7.9548. Min Act: -0.1700
Data Index: 2458687 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7986. Min Range: -8.7986
Max Act: 7.9236. Min Act: -0.1700
Data Index: 2749354 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7986. Min Range: -8.7986
Max Act: 7.8923. Min Act: -0.1700
Data Index: 3514409 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7986. Min Range: -8.7986
Max Act: 7.8923. Min Act: -0.1700
Data Index: 6637681 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7986. Min Range: -8.7986
Max Act: 7.8923. Min Act: -0.1700
Data Index: 157462 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7986. Min Range: -8.7986
Max Act: 7.8611. Min Act: -0.1700
Data Index: 2897024 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19