Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 107 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2412. Min Range: -8.2412
Max Act: 8.2412. Min Act: -0.1700
Data Index: 8333989 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2412. Min Range: -8.2412
Max Act: 8.2412. Min Act: -0.1700
Data Index: 3896320 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2412. Min Range: -8.2412
Max Act: 8.1787. Min Act: -0.1700
Data Index: 903937 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2412. Min Range: -8.2412
Max Act: 8.1162. Min Act: -0.1700
Data Index: 7509169 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2412. Min Range: -8.2412
Max Act: 8.2412. Min Act: -0.1700
Data Index: 1789977 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2412. Min Range: -8.2412
Max Act: 8.1162. Min Act: -0.1700
Data Index: 932854 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2412. Min Range: -8.2412
Max Act: 8.1162. Min Act: -0.1700
Data Index: 8372596 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2412. Min Range: -8.2412
Max Act: 8.1787. Min Act: -0.1700
Data Index: 6101985 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2412. Min Range: -8.2412
Max Act: 8.1162. Min Act: -0.1700
Data Index: 4356025 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2412. Min Range: -8.2412
Max Act: 8.0537. Min Act: -0.1700
Data Index: 6256524 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2412. Min Range: -8.2412
Max Act: 7.9287. Min Act: -0.1700
Data Index: 6956589 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2412. Min Range: -8.2412
Max Act: 7.9287. Min Act: -0.1700
Data Index: 6571891 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2412. Min Range: -8.2412
Max Act: 7.9912. Min Act: -0.1700
Data Index: 5300732 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2412. Min Range: -8.2412
Max Act: 7.9287. Min Act: -0.1700
Data Index: 2474648 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2412. Min Range: -8.2412
Max Act: 7.9287. Min Act: -0.1700
Data Index: 5060638 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2412. Min Range: -8.2412
Max Act: 7.9287. Min Act: -0.1700
Data Index: 2765985 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2412. Min Range: -8.2412
Max Act: 7.9287. Min Act: -0.1700
Data Index: 8779440 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2412. Min Range: -8.2412
Max Act: 7.9287. Min Act: -0.1700
Data Index: 1427745 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2412. Min Range: -8.2412
Max Act: 7.9287. Min Act: -0.1699
Data Index: 5492893 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2412. Min Range: -8.2412
Max Act: 7.8662. Min Act: -0.1700
Data Index: 4254298 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19