Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3971 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0323. Min Range: -3.0323
Max Act: 3.0323. Min Act: -0.1700
Data Index: 5365837 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.8899. Min Act: -0.1700
Data Index: 1907669 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.9216. Min Act: -0.1700
Data Index: 2016534 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.8740. Min Act: -0.1700
Data Index: 6604703 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.8740. Min Act: -0.1700
Data Index: 3232594 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7945. Min Act: -0.1700
Data Index: 2241610 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7626. Min Act: -0.1700
Data Index: 6259395 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7626. Min Act: -0.1700
Data Index: 4593112 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7307. Min Act: -0.1700
Data Index: 8531581 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7307. Min Act: -0.1700
Data Index: 7501708 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7467. Min Act: -0.1700
Data Index: 4806767 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7467. Min Act: -0.1700
Data Index: 4417222 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7307. Min Act: -0.1700
Data Index: 2102725 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7626. Min Act: -0.1700
Data Index: 6606609 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7467. Min Act: -0.1700
Data Index: 4234906 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7147. Min Act: -0.1700
Data Index: 5622142 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.6827. Min Act: -0.1700
Data Index: 2498410 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.6827. Min Act: -0.1700
Data Index: 5921136 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7307. Min Act: -0.1700
Data Index: 5447609 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0323. Min Range: -3.0323
Max Act: 2.7147. Min Act: -0.1700
Data Index: 981449 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19