Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5364 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.5628. Min Act: -0.1700
Data Index: 6286895 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.5628. Min Act: -0.1700
Data Index: 929696 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.5315. Min Act: -0.1700
Data Index: 2984418 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.4065. Min Act: -0.1700
Data Index: 5862673 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.2503. Min Act: -0.1700
Data Index: 455405 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.2190. Min Act: -0.1700
Data Index: 5682874 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.1252. Min Act: -0.1700
Data Index: 6626398 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0940. Min Act: -0.1700
Data Index: 7249175 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0627. Min Act: -0.1700
Data Index: 1609232 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0627. Min Act: -0.1700
Data Index: 8229789 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0627. Min Act: -0.1700
Data Index: 3484954 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0940. Min Act: -0.1700
Data Index: 2374191 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0627. Min Act: -0.1700
Data Index: 3118859 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0002. Min Act: -0.1700
Data Index: 4807915 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0315. Min Act: -0.1700
Data Index: 8252079 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0315. Min Act: -0.1700
Data Index: 3279110 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0315. Min Act: -0.1700
Data Index: 5305863 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0002. Min Act: -0.1700
Data Index: 6564706 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0002. Min Act: -0.1700
Data Index: 4311579 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5628. Min Range: -4.5628
Max Act: 4.0002. Min Act: -0.1700
Data Index: 505630 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19