Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6979. Min Range: -8.6979
Max Act: 8.6979. Min Act: -0.1700
Data Index: 5487250 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.5104. Min Act: -0.1700
Data Index: 7474680 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.3541. Min Act: -0.1700
Data Index: 4750800 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.3541. Min Act: -0.1700
Data Index: 2642803 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.1979. Min Act: -0.1700
Data Index: 929327 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.1666. Min Act: -0.1700
Data Index: 7990720 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.1041. Min Act: -0.1700
Data Index: 8766019 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.0729. Min Act: -0.1700
Data Index: 4930015 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.0729. Min Act: -0.1700
Data Index: 2713033 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.0104. Min Act: -0.1700
Data Index: 5536249 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.0416. Min Act: -0.1700
Data Index: 5933213 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.0104. Min Act: -0.1700
Data Index: 2684725 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6979. Min Range: -8.6979
Max Act: 6.9791. Min Act: -0.1700
Data Index: 5271358 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6979. Min Range: -8.6979
Max Act: 7.0104. Min Act: -0.1700
Data Index: 3476494 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6979. Min Range: -8.6979
Max Act: 6.8854. Min Act: -0.1700
Data Index: 7399862 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6979. Min Range: -8.6979
Max Act: 6.9166. Min Act: -0.1700
Data Index: 7198774 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6979. Min Range: -8.6979
Max Act: 6.9166. Min Act: -0.1700
Data Index: 681141 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6979. Min Range: -8.6979
Max Act: 6.8541. Min Act: -0.1700
Data Index: 5397388 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6979. Min Range: -8.6979
Max Act: 6.8229. Min Act: -0.1700
Data Index: 4013843 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6979. Min Range: -8.6979
Max Act: 6.7916. Min Act: -0.1700
Data Index: 6266009 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19