Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1859. Min Range: -8.1859
Max Act: 8.1859. Min Act: -0.1700
Data Index: 511239 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.8734. Min Act: -0.1700
Data Index: 5472264 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.8734. Min Act: -0.1700
Data Index: 3096227 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.8734. Min Act: -0.1700
Data Index: 6127279 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.8109. Min Act: -0.1700
Data Index: 808186 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.8109. Min Act: -0.1700
Data Index: 7435652 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.7484. Min Act: -0.1700
Data Index: 1140560 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.7484. Min Act: -0.1700
Data Index: 3031303 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6859. Min Act: -0.1700
Data Index: 399138 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.7484. Min Act: -0.1700
Data Index: 7423612 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6859. Min Act: -0.1700
Data Index: 1805475 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6859. Min Act: -0.1700
Data Index: 4353135 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6859. Min Act: -0.1700
Data Index: 2593780 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6859. Min Act: -0.1700
Data Index: 698279 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6859. Min Act: -0.1700
Data Index: 7396835 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6234. Min Act: -0.1700
Data Index: 7051606 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6234. Min Act: -0.1700
Data Index: 4932096 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6234. Min Act: -0.1700
Data Index: 7189910 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6234. Min Act: -0.1700
Data Index: 6434052 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1859. Min Range: -8.1859
Max Act: 7.6234. Min Act: -0.1700
Data Index: 3253554 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19