Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5729. Min Range: -8.5729
Max Act: 8.5729. Min Act: -0.1700
Data Index: 4025985 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5729. Min Range: -8.5729
Max Act: 8.4479. Min Act: -0.1700
Data Index: 5682820 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5729. Min Range: -8.5729
Max Act: 8.1354. Min Act: -0.1700
Data Index: 7341274 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5729. Min Range: -8.5729
Max Act: 8.1354. Min Act: -0.1700
Data Index: 2470642 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5729. Min Range: -8.5729
Max Act: 8.1354. Min Act: -0.1700
Data Index: 2931715 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5729. Min Range: -8.5729
Max Act: 8.0104. Min Act: -0.1700
Data Index: 573723 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5729. Min Range: -8.5729
Max Act: 8.0104. Min Act: -0.1700
Data Index: 8545811 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.9479. Min Act: -0.1700
Data Index: 3742344 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.9479. Min Act: -0.1700
Data Index: 6026403 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.8854. Min Act: -0.1700
Data Index: 2680439 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.8854. Min Act: -0.1700
Data Index: 6475080 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.8229. Min Act: -0.1700
Data Index: 2186347 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.8229. Min Act: -0.1700
Data Index: 3957968 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.8229. Min Act: -0.1700
Data Index: 3605677 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.8229. Min Act: -0.1700
Data Index: 5590640 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.8229. Min Act: -0.1700
Data Index: 6397494 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.7604. Min Act: -0.1700
Data Index: 3646558 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.7604. Min Act: -0.1700
Data Index: 7714616 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.6979. Min Act: -0.1700
Data Index: 3635282 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5729. Min Range: -8.5729
Max Act: 7.6979. Min Act: -0.1700
Data Index: 3999721 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19