Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.6236. Min Act: -0.1700
Data Index: 5528495 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.4673. Min Act: -0.1700
Data Index: 80956 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.4048. Min Act: -0.1700
Data Index: 7843758 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.3736. Min Act: -0.1700
Data Index: 14203 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.3111. Min Act: -0.1700
Data Index: 7843759 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2798. Min Act: -0.1700
Data Index: 5258829 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.1861. Min Act: -0.1700
Data Index: 6384429 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2173. Min Act: -0.1700
Data Index: 8140574 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.1861. Min Act: -0.1700
Data Index: 1906893 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.1861. Min Act: -0.1700
Data Index: 7583697 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.1861. Min Act: -0.1700
Data Index: 5723040 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.1548. Min Act: -0.1700
Data Index: 7800020 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.1548. Min Act: -0.1700
Data Index: 2277186 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.0923. Min Act: -0.1700
Data Index: 4031022 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.1236. Min Act: -0.1700
Data Index: 6662471 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.0923. Min Act: -0.1700
Data Index: 7726213 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.0611. Min Act: -0.1700
Data Index: 5871779 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.0611. Min Act: -0.1700
Data Index: 58894 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.0611. Min Act: -0.1700
Data Index: 457533 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.0298. Min Act: -0.1700
Data Index: 2149818 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19