Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 729 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.8942. Min Act: -0.1700
Data Index: 1453301 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.7692. Min Act: -0.1700
Data Index: 4217440 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.7067. Min Act: -0.1700
Data Index: 5759041 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.6442. Min Act: -0.1700
Data Index: 3583940 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.6442. Min Act: -0.1700
Data Index: 5623538 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.6442. Min Act: -0.1700
Data Index: 6169544 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.5817. Min Act: -0.1700
Data Index: 6178579 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.5192. Min Act: -0.1700
Data Index: 6810356 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.5192. Min Act: -0.1700
Data Index: 5428192 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.5192. Min Act: -0.1700
Data Index: 7866331 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.4567. Min Act: -0.1700
Data Index: 221789 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.5817. Min Act: -0.1700
Data Index: 8166516 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.5192. Min Act: -0.1700
Data Index: 6604767 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.5192. Min Act: -0.1700
Data Index: 6178576 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.4567. Min Act: -0.1700
Data Index: 145370 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.3942. Min Act: -0.1700
Data Index: 4145189 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.3942. Min Act: -0.1700
Data Index: 7625133 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.3942. Min Act: -0.1700
Data Index: 1715459 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.3942. Min Act: -0.1700
Data Index: 2418172 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8942. Min Range: -7.8942
Max Act: 7.3629. Min Act: -0.1700
Data Index: 7772842 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19