Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1887 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6554. Min Range: -6.6554
Max Act: 6.6554. Min Act: -0.1700
Data Index: 7848441 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6554. Min Range: -6.6554
Max Act: 6.3742. Min Act: -0.1700
Data Index: 2968489 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6554. Min Range: -6.6554
Max Act: 6.1554. Min Act: -0.1700
Data Index: 6461060 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6554. Min Range: -6.6554
Max Act: 6.1242. Min Act: -0.1700
Data Index: 7289329 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6554. Min Range: -6.6554
Max Act: 6.0929. Min Act: -0.1700
Data Index: 2237675 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6554. Min Range: -6.6554
Max Act: 6.0617. Min Act: -0.1700
Data Index: 5491368 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6554. Min Range: -6.6554
Max Act: 6.0617. Min Act: -0.1700
Data Index: 7158136 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.9992. Min Act: -0.1700
Data Index: 8216473 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6554. Min Range: -6.6554
Max Act: 6.0304. Min Act: -0.1700
Data Index: 4848128 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.9992. Min Act: -0.1700
Data Index: 7099899 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.9679. Min Act: -0.1700
Data Index: 6496245 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.9992. Min Act: -0.1700
Data Index: 1131526 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.9054. Min Act: -0.1700
Data Index: 1908103 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.8742. Min Act: -0.1700
Data Index: 5917100 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.8742. Min Act: -0.1700
Data Index: 4305596 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.9367. Min Act: -0.1700
Data Index: 7934448 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.9054. Min Act: -0.1700
Data Index: 360743 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.8429. Min Act: -0.1700
Data Index: 1348100 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.8429. Min Act: -0.1700
Data Index: 3908206 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6554. Min Range: -6.6554
Max Act: 5.8742. Min Act: -0.1700
Data Index: 6950727 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19