Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3739 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1229. Min Range: -11.1229
Max Act: 11.1229. Min Act: -0.1700
Data Index: 4107102 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1229. Min Range: -11.1229
Max Act: 11.0604. Min Act: -0.1700
Data Index: 4419898 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.9979. Min Act: -0.1700
Data Index: 4419900 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.9979. Min Act: -0.1700
Data Index: 1853436 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.9354. Min Act: -0.1700
Data Index: 405365 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.8729. Min Act: -0.1700
Data Index: 670677 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.8729. Min Act: -0.1700
Data Index: 4703924 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.8104. Min Act: -0.1700
Data Index: 76622 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.7479. Min Act: -0.1700
Data Index: 4419901 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.7479. Min Act: -0.1700
Data Index: 4234887 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.6854. Min Act: -0.1700
Data Index: 6581977 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.6229. Min Act: -0.1700
Data Index: 7761023 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.6229. Min Act: -0.1700
Data Index: 6185388 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.6229. Min Act: -0.1700
Data Index: 670678 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.6229. Min Act: -0.1700
Data Index: 3833016 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.4979. Min Act: -0.1700
Data Index: 7668651 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.5604. Min Act: -0.1700
Data Index: 5396837 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.4979. Min Act: -0.1700
Data Index: 315169 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.4979. Min Act: -0.1700
Data Index: 5629844 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1229. Min Range: -11.1229
Max Act: 10.4979. Min Act: -0.1700
Data Index: 1979996 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19