Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5748. Min Range: -5.5748
Max Act: 5.5748. Min Act: -0.1700
Data Index: 5547310 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5748. Min Range: -5.5748
Max Act: 5.2310. Min Act: -0.1700
Data Index: 5133209 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5748. Min Range: -5.5748
Max Act: 5.1685. Min Act: -0.1700
Data Index: 2266631 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5748. Min Range: -5.5748
Max Act: 5.0748. Min Act: -0.1700
Data Index: 5727038 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5748. Min Range: -5.5748
Max Act: 5.0123. Min Act: -0.1700
Data Index: 7497267 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.9810. Min Act: -0.1700
Data Index: 2410263 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.9185. Min Act: -0.1700
Data Index: 1155197 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.9185. Min Act: -0.1700
Data Index: 6203331 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.8873. Min Act: -0.1700
Data Index: 1155196 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.8560. Min Act: -0.1700
Data Index: 4461643 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.8560. Min Act: -0.1700
Data Index: 8055390 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.8560. Min Act: -0.1700
Data Index: 7388198 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.8248. Min Act: -0.1700
Data Index: 794380 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.8248. Min Act: -0.1700
Data Index: 1843167 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.7935. Min Act: -0.1700
Data Index: 5999722 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.7935. Min Act: -0.1700
Data Index: 4911471 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.7935. Min Act: -0.1700
Data Index: 4074285 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.7623. Min Act: -0.1700
Data Index: 7520015 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.7623. Min Act: -0.1700
Data Index: 8737425 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5748. Min Range: -5.5748
Max Act: 4.7623. Min Act: -0.1700
Data Index: 5570185 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19