Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5471 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.7577. Min Act: -0.1700
Data Index: 4770368 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.7577. Min Act: -0.1700
Data Index: 1689755 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.6327. Min Act: -0.1700
Data Index: 5326046 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.6639. Min Act: -0.1700
Data Index: 82149 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.6639. Min Act: -0.1700
Data Index: 184541 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.6327. Min Act: -0.1700
Data Index: 1868708 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.5702. Min Act: -0.1700
Data Index: 716853 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.5389. Min Act: -0.1700
Data Index: 5303192 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.5389. Min Act: -0.1700
Data Index: 6511705 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.5077. Min Act: -0.1700
Data Index: 6208966 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.5077. Min Act: -0.1700
Data Index: 4755891 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.5077. Min Act: -0.1700
Data Index: 5218444 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.4764. Min Act: -0.1700
Data Index: 6327362 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.4764. Min Act: -0.1700
Data Index: 1511432 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.5077. Min Act: -0.1700
Data Index: 4308698 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.4764. Min Act: -0.1700
Data Index: 5561057 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.4139. Min Act: -0.1700
Data Index: 768004 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.4764. Min Act: -0.1700
Data Index: 2199362 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.4139. Min Act: -0.1700
Data Index: 1040411 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7577. Min Range: -6.7577
Max Act: 6.4139. Min Act: -0.1700
Data Index: 7914577 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19