Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3836 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.7365. Min Act: -0.1700
Data Index: 3794352 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.6740. Min Act: -0.1700
Data Index: 6748661 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.6740. Min Act: -0.1700
Data Index: 8416900 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.6427. Min Act: -0.1700
Data Index: 1628959 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.6427. Min Act: -0.1700
Data Index: 3611149 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.6740. Min Act: -0.1700
Data Index: 1877397 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.6427. Min Act: -0.1700
Data Index: 3755229 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.6115. Min Act: -0.1700
Data Index: 6041312 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.6427. Min Act: -0.1700
Data Index: 6913003 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.6427. Min Act: -0.1700
Data Index: 4714727 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.5802. Min Act: -0.1699
Data Index: 5956186 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.5802. Min Act: -0.1700
Data Index: 465617 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.5802. Min Act: -0.1700
Data Index: 5936358 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.6115. Min Act: -0.1698
Data Index: 707060 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.5802. Min Act: -0.1700
Data Index: 4449296 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.5490. Min Act: -0.1700
Data Index: 7030512 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.5802. Min Act: -0.1700
Data Index: 4744821 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.5490. Min Act: -0.1700
Data Index: 8496239 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.5490. Min Act: -0.1698
Data Index: 6418081 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7365. Min Range: -5.7365
Max Act: 5.5490. Min Act: -0.1700
Data Index: 1008133 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19