Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.3725. Min Act: -0.1700
Data Index: 8738425 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.3725. Min Act: -0.1700
Data Index: 3328716 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.3397. Min Act: -0.1700
Data Index: 713443 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.3233. Min Act: -0.1700
Data Index: 7171001 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.3233. Min Act: -0.1700
Data Index: 1697155 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.3069. Min Act: -0.1700
Data Index: 75644 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2905. Min Act: -0.1700
Data Index: 220765 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2905. Min Act: -0.1700
Data Index: 5358577 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2740. Min Act: -0.1700
Data Index: 8407922 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2740. Min Act: -0.1700
Data Index: 2859370 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2740. Min Act: -0.1700
Data Index: 8755652 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2740. Min Act: -0.1700
Data Index: 5358575 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2740. Min Act: -0.1700
Data Index: 496514 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2740. Min Act: -0.1700
Data Index: 7843314 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2575. Min Act: -0.1700
Data Index: 8407912 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2410. Min Act: -0.1700
Data Index: 1427446 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2575. Min Act: -0.1700
Data Index: 6310294 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2575. Min Act: -0.1700
Data Index: 3756182 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2575. Min Act: -0.1700
Data Index: 6378589 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3725. Min Range: -2.3725
Max Act: 2.2410. Min Act: -0.1700
Data Index: 4150871 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19