Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1986. Min Range: -8.1986
Max Act: 8.1986. Min Act: -0.1700
Data Index: 869058 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1986. Min Range: -8.1986
Max Act: 8.1361. Min Act: -0.1700
Data Index: 3480636 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.9798. Min Act: -0.1700
Data Index: 7999422 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1986. Min Range: -8.1986
Max Act: 8.0111. Min Act: -0.1700
Data Index: 3290667 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.9486. Min Act: -0.1700
Data Index: 8706328 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.9798. Min Act: -0.1700
Data Index: 6560664 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.9173. Min Act: -0.1700
Data Index: 5907910 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.9173. Min Act: -0.1700
Data Index: 2151949 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.8548. Min Act: -0.1700
Data Index: 6141019 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.8236. Min Act: -0.1700
Data Index: 49756 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.7923. Min Act: -0.1700
Data Index: 6386823 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.7611. Min Act: -0.1700
Data Index: 1680320 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.7923. Min Act: -0.1700
Data Index: 2163150 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.7611. Min Act: -0.1700
Data Index: 3290631 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.7611. Min Act: -0.1700
Data Index: 2448110 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.7298. Min Act: -0.1700
Data Index: 3270162 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.7298. Min Act: -0.1700
Data Index: 5458441 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.7298. Min Act: -0.1700
Data Index: 8173124 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.6986. Min Act: -0.1700
Data Index: 3290630 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1986. Min Range: -8.1986
Max Act: 7.6673. Min Act: -0.1700
Data Index: 7287474 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19