Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2723 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.9704. Min Act: -0.1700
Data Index: 898217 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.9704. Min Act: -0.1700
Data Index: 593827 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.9392. Min Act: -0.1700
Data Index: 796229 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.7829. Min Act: -0.1700
Data Index: 7129679 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.7517. Min Act: -0.1700
Data Index: 579981 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.7829. Min Act: -0.1700
Data Index: 2905024 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6892. Min Act: -0.1700
Data Index: 1008199 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.7204. Min Act: -0.1700
Data Index: 1630724 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6892. Min Act: -0.1700
Data Index: 1222987 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6579. Min Act: -0.1700
Data Index: 4204269 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6579. Min Act: -0.1700
Data Index: 2896156 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6267. Min Act: -0.1700
Data Index: 721794 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6267. Min Act: -0.1700
Data Index: 3962079 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5954. Min Act: -0.1700
Data Index: 2457316 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5642. Min Act: -0.1700
Data Index: 1764081 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5954. Min Act: -0.1700
Data Index: 8548170 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5642. Min Act: -0.1700
Data Index: 6369592 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5642. Min Act: -0.1700
Data Index: 7776502 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5642. Min Act: -0.1700
Data Index: 5879336 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5642. Min Act: -0.1700
Data Index: 7522047 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19