Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.6632. Min Act: -0.1700
Data Index: 3780724 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.6476. Min Act: -0.1700
Data Index: 7272731 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.6476. Min Act: -0.1700
Data Index: 5420788 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.6319. Min Act: -0.1700
Data Index: 8459845 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.5537. Min Act: -0.1700
Data Index: 1565390 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.5537. Min Act: -0.1700
Data Index: 6356708 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.5537. Min Act: -0.1700
Data Index: 6490291 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.5380. Min Act: -0.1700
Data Index: 1975472 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.5067. Min Act: -0.1700
Data Index: 5063431 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.5067. Min Act: -0.1700
Data Index: 282316 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.4910. Min Act: -0.1700
Data Index: 3965931 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.4754. Min Act: -0.1700
Data Index: 5400928 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.4597. Min Act: -0.1700
Data Index: 962806 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.4597. Min Act: -0.1700
Data Index: 6192181 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.4597. Min Act: -0.1700
Data Index: 700014 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.4440. Min Act: -0.1700
Data Index: 130728 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.4597. Min Act: -0.1700
Data Index: 1402553 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.4284. Min Act: -0.1700
Data Index: 972614 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.4127. Min Act: -0.1700
Data Index: 7470490 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6632. Min Range: -3.6632
Max Act: 3.3970. Min Act: -0.1700
Data Index: 3907165 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19