Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 92 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.2265. Min Act: -0.1700
Data Index: 1131160 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.2265. Min Act: -0.1700
Data Index: 5035062 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1953. Min Act: -0.1700
Data Index: 4391878 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1640. Min Act: -0.1700
Data Index: 7336757 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1953. Min Act: -0.1700
Data Index: 2998721 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1328. Min Act: -0.1700
Data Index: 986671 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1328. Min Act: -0.1700
Data Index: 767473 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1328. Min Act: -0.1700
Data Index: 1592083 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1640. Min Act: -0.1700
Data Index: 6725645 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1640. Min Act: -0.1700
Data Index: 6132792 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1015. Min Act: -0.1700
Data Index: 92900 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1015. Min Act: -0.1700
Data Index: 4665303 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1015. Min Act: -0.1700
Data Index: 584782 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1015. Min Act: -0.1700
Data Index: 367177 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1015. Min Act: -0.1700
Data Index: 762060 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1015. Min Act: -0.1700
Data Index: 74751 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1015. Min Act: -0.1700
Data Index: 4558681 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1015. Min Act: -0.1700
Data Index: 576475 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1015. Min Act: -0.1700
Data Index: 3029363 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2265. Min Range: -5.2265
Max Act: 5.1015. Min Act: -0.1700
Data Index: 5963608 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19