Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3294. Min Range: -6.3294
Max Act: 6.3294. Min Act: -0.1700
Data Index: 5827320 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3294. Min Range: -6.3294
Max Act: 6.1731. Min Act: -0.1700
Data Index: 1019574 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3294. Min Range: -6.3294
Max Act: 6.1106. Min Act: -0.1700
Data Index: 8211251 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3294. Min Range: -6.3294
Max Act: 6.1106. Min Act: -0.1700
Data Index: 2943356 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3294. Min Range: -6.3294
Max Act: 6.0794. Min Act: -0.1700
Data Index: 735022 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3294. Min Range: -6.3294
Max Act: 6.0481. Min Act: -0.1700
Data Index: 4757582 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3294. Min Range: -6.3294
Max Act: 6.0169. Min Act: -0.1700
Data Index: 5809557 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3294. Min Range: -6.3294
Max Act: 6.0169. Min Act: -0.1700
Data Index: 8545343 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3294. Min Range: -6.3294
Max Act: 6.0169. Min Act: -0.1700
Data Index: 5851954 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3294. Min Range: -6.3294
Max Act: 6.0169. Min Act: -0.1700
Data Index: 6924184 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3294. Min Range: -6.3294
Max Act: 5.9231. Min Act: -0.1700
Data Index: 5865132 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3294. Min Range: -6.3294
Max Act: 5.9231. Min Act: -0.1700
Data Index: 5352531 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3294. Min Range: -6.3294
Max Act: 5.9231. Min Act: -0.1700
Data Index: 4326632 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3294. Min Range: -6.3294
Max Act: 5.8919. Min Act: -0.1700
Data Index: 1362145 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3294. Min Range: -6.3294
Max Act: 5.8919. Min Act: -0.1700
Data Index: 8765869 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3294. Min Range: -6.3294
Max Act: 5.8919. Min Act: -0.1700
Data Index: 6618451 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3294. Min Range: -6.3294
Max Act: 5.8606. Min Act: -0.1700
Data Index: 6876600 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3294. Min Range: -6.3294
Max Act: 5.8294. Min Act: -0.1700
Data Index: 6480469 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3294. Min Range: -6.3294
Max Act: 5.7981. Min Act: -0.1700
Data Index: 6849543 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3294. Min Range: -6.3294
Max Act: 5.8294. Min Act: -0.1700
Data Index: 5483911 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19