Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6105 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.4204. Min Act: -0.1700
Data Index: 3725397 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.2641. Min Act: -0.1700
Data Index: 6172746 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.2954. Min Act: -0.1700
Data Index: 7963898 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.2329. Min Act: -0.1700
Data Index: 7667960 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.1391. Min Act: -0.1700
Data Index: 6752391 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.1079. Min Act: -0.1700
Data Index: 5918234 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.1079. Min Act: -0.1700
Data Index: 1502778 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.1391. Min Act: -0.1700
Data Index: 8793502 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.0766. Min Act: -0.1700
Data Index: 8284588 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.0766. Min Act: -0.1700
Data Index: 2170260 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4204. Min Range: -7.4204
Max Act: 7.0454. Min Act: -0.1700
Data Index: 6407914 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4204. Min Range: -7.4204
Max Act: 6.9829. Min Act: -0.1700
Data Index: 6081246 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4204. Min Range: -7.4204
Max Act: 6.9829. Min Act: -0.1700
Data Index: 3525209 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4204. Min Range: -7.4204
Max Act: 6.9516. Min Act: -0.1700
Data Index: 4409727 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4204. Min Range: -7.4204
Max Act: 6.9204. Min Act: -0.1700
Data Index: 2978074 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4204. Min Range: -7.4204
Max Act: 6.9516. Min Act: -0.1700
Data Index: 446509 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4204. Min Range: -7.4204
Max Act: 6.9516. Min Act: -0.1700
Data Index: 1943380 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4204. Min Range: -7.4204
Max Act: 6.9204. Min Act: -0.1700
Data Index: 1903074 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4204. Min Range: -7.4204
Max Act: 6.9204. Min Act: -0.1700
Data Index: 7474342 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4204. Min Range: -7.4204
Max Act: 6.9204. Min Act: -0.1700
Data Index: 5799468 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19