Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3228 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3204. Min Range: -6.3204
Max Act: 6.3204. Min Act: -0.1700
Data Index: 6753416 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3204. Min Range: -6.3204
Max Act: 6.0391. Min Act: -0.1700
Data Index: 7055665 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3204. Min Range: -6.3204
Max Act: 6.0079. Min Act: -0.1700
Data Index: 3917614 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.9454. Min Act: -0.1700
Data Index: 1715462 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.9141. Min Act: -0.1700
Data Index: 3544449 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.8829. Min Act: -0.1700
Data Index: 2234591 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.8516. Min Act: -0.1700
Data Index: 1375903 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.8516. Min Act: -0.1700
Data Index: 1729046 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.8516. Min Act: -0.1700
Data Index: 51326 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.8204. Min Act: -0.1700
Data Index: 1965224 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.8204. Min Act: -0.1700
Data Index: 7872916 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.7891. Min Act: -0.1700
Data Index: 2746541 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.7579. Min Act: -0.1700
Data Index: 1953666 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.7266. Min Act: -0.1700
Data Index: 4526474 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.7266. Min Act: -0.1700
Data Index: 6850583 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.7266. Min Act: -0.1700
Data Index: 5055281 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.7266. Min Act: -0.1700
Data Index: 3896850 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.6641. Min Act: -0.1700
Data Index: 3597845 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.6954. Min Act: -0.1700
Data Index: 928307 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3204. Min Range: -6.3204
Max Act: 5.6954. Min Act: -0.1700
Data Index: 3626303 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19