Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.6941. Min Act: -0.1700
Data Index: 5319991 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.6316. Min Act: -0.1700
Data Index: 4471526 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.3816. Min Act: -0.1700
Data Index: 7994289 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.3816. Min Act: -0.1700
Data Index: 6077635 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.3503. Min Act: -0.1700
Data Index: 5319992 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.3191. Min Act: -0.1700
Data Index: 7963593 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.2878. Min Act: -0.1700
Data Index: 1073869 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.2253. Min Act: -0.1700
Data Index: 4317053 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.2253. Min Act: -0.1700
Data Index: 7108423 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.1941. Min Act: -0.1700
Data Index: 7745238 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.2566. Min Act: -0.1700
Data Index: 3485054 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.1941. Min Act: -0.1700
Data Index: 4705273 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.1628. Min Act: -0.1700
Data Index: 5768337 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.1628. Min Act: -0.1700
Data Index: 1697589 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.0691. Min Act: -0.1700
Data Index: 3706856 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.1003. Min Act: -0.1700
Data Index: 6664996 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.1003. Min Act: -0.1700
Data Index: 5867528 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.1003. Min Act: -0.1700
Data Index: 6711596 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.1003. Min Act: -0.1700
Data Index: 5319989 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6941. Min Range: -6.6941
Max Act: 6.1003. Min Act: -0.1700
Data Index: 5905678 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19