Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2212 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0292. Min Range: -6.0292
Max Act: 6.0292. Min Act: -0.1700
Data Index: 2466133 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.9979. Min Act: -0.1700
Data Index: 2914675 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.9667. Min Act: -0.1700
Data Index: 7689993 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.9354. Min Act: -0.1700
Data Index: 8237581 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.9042. Min Act: -0.1700
Data Index: 8586124 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.8729. Min Act: -0.1700
Data Index: 1434658 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.8729. Min Act: -0.1700
Data Index: 2914666 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.8104. Min Act: -0.1700
Data Index: 8270112 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.8417. Min Act: -0.1700
Data Index: 2326836 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.7792. Min Act: -0.1700
Data Index: 4610596 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.7479. Min Act: -0.1700
Data Index: 7668017 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.7479. Min Act: -0.1700
Data Index: 3650359 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.7479. Min Act: -0.1700
Data Index: 3115065 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.7479. Min Act: -0.1700
Data Index: 3773225 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.7167. Min Act: -0.1700
Data Index: 3982997 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.7167. Min Act: -0.1700
Data Index: 7604533 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.6854. Min Act: -0.1700
Data Index: 8448444 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.7167. Min Act: -0.1700
Data Index: 1370104 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.6854. Min Act: -0.1700
Data Index: 7396167 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0292. Min Range: -6.0292
Max Act: 5.6854. Min Act: -0.1700
Data Index: 1150349 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19