Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.6864. Min Act: -0.1700
Data Index: 1896637 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.5925. Min Act: -0.1700
Data Index: 4384107 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.5769. Min Act: -0.1700
Data Index: 7444952 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.5143. Min Act: -0.1700
Data Index: 7951508 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.5456. Min Act: -0.1700
Data Index: 3183237 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.5143. Min Act: -0.1700
Data Index: 676487 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.4829. Min Act: -0.1700
Data Index: 6955615 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.4516. Min Act: -0.1700
Data Index: 3824723 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.4203. Min Act: -0.1700
Data Index: 5505329 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.4359. Min Act: -0.1700
Data Index: 648081 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.4046. Min Act: -0.1700
Data Index: 4201827 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.4046. Min Act: -0.1700
Data Index: 332516 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.4046. Min Act: -0.1700
Data Index: 5565187 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.4046. Min Act: -0.1700
Data Index: 2685980 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.3575. Min Act: -0.1700
Data Index: 960708 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.3418. Min Act: -0.1700
Data Index: 5161400 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.3418. Min Act: -0.1700
Data Index: 4468551 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.3262. Min Act: -0.1700
Data Index: 6235435 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.3418. Min Act: -0.1700
Data Index: 6089854 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6864. Min Range: -3.6864
Max Act: 3.3105. Min Act: -0.1700
Data Index: 5055336 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19