Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.7727. Min Act: -0.1700
Data Index: 2816245 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.6632. Min Act: -0.1700
Data Index: 3427528 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.6632. Min Act: -0.1700
Data Index: 3987666 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.6476. Min Act: -0.1700
Data Index: 645459 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.6006. Min Act: -0.1700
Data Index: 1516069 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5850. Min Act: -0.1700
Data Index: 8799629 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5380. Min Act: -0.1700
Data Index: 7610660 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5380. Min Act: -0.1700
Data Index: 5987749 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5380. Min Act: -0.1700
Data Index: 3336230 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5380. Min Act: -0.1700
Data Index: 5515031 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5380. Min Act: -0.1700
Data Index: 6234088 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5380. Min Act: -0.1700
Data Index: 412604 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5067. Min Act: -0.1700
Data Index: 3609212 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5224. Min Act: -0.1700
Data Index: 5442288 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5067. Min Act: -0.1700
Data Index: 475248 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.5067. Min Act: -0.1700
Data Index: 8136354 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.4910. Min Act: -0.1700
Data Index: 163213 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.4910. Min Act: -0.1700
Data Index: 8039042 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.4754. Min Act: -0.1700
Data Index: 7332608 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7727. Min Range: -3.7727
Max Act: 3.4754. Min Act: -0.1700
Data Index: 5836105 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19