Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1704. Min Range: -4.1704
Max Act: 4.1704. Min Act: -0.1700
Data Index: 8742629 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1704. Min Range: -4.1704
Max Act: 4.1391. Min Act: -0.1700
Data Index: 7942752 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1704. Min Range: -4.1704
Max Act: 4.0453. Min Act: -0.1700
Data Index: 8201608 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9828. Min Act: -0.1700
Data Index: 2265282 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9516. Min Act: -0.1700
Data Index: 8523200 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9516. Min Act: -0.1700
Data Index: 6035309 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9516. Min Act: -0.1700
Data Index: 5108786 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9516. Min Act: -0.1700
Data Index: 4503170 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9203. Min Act: -0.1700
Data Index: 3375262 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9203. Min Act: -0.1700
Data Index: 6035296 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9203. Min Act: -0.1700
Data Index: 6604436 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9516. Min Act: -0.1700
Data Index: 3636588 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9203. Min Act: -0.1700
Data Index: 953223 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9203. Min Act: -0.1700
Data Index: 4797599 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9203. Min Act: -0.1700
Data Index: 8559994 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9516. Min Act: -0.1700
Data Index: 6035302 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9203. Min Act: -0.1700
Data Index: 3882733 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9203. Min Act: -0.1700
Data Index: 8051405 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9203. Min Act: -0.1700
Data Index: 953241 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1704. Min Range: -4.1704
Max Act: 3.9203. Min Act: -0.1700
Data Index: 8787191 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19