Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 499 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4861. Min Range: -8.4861
Max Act: 8.4861. Min Act: -0.1700
Data Index: 816967 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4861. Min Range: -8.4861
Max Act: 8.4236. Min Act: -0.1700
Data Index: 4724009 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4861. Min Range: -8.4861
Max Act: 8.2361. Min Act: -0.1700
Data Index: 7615035 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4861. Min Range: -8.4861
Max Act: 8.1736. Min Act: -0.1700
Data Index: 781931 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4861. Min Range: -8.4861
Max Act: 8.1111. Min Act: -0.1700
Data Index: 7704219 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4861. Min Range: -8.4861
Max Act: 8.1111. Min Act: -0.1700
Data Index: 5000875 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4861. Min Range: -8.4861
Max Act: 8.0486. Min Act: -0.1700
Data Index: 5683113 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4861. Min Range: -8.4861
Max Act: 8.0486. Min Act: -0.1700
Data Index: 4111387 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.9236. Min Act: -0.1700
Data Index: 5386830 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.9861. Min Act: -0.1700
Data Index: 642226 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.9236. Min Act: -0.1700
Data Index: 1457345 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.9236. Min Act: -0.1700
Data Index: 4667729 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.9236. Min Act: -0.1700
Data Index: 1213596 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.9236. Min Act: -0.1700
Data Index: 7163220 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.9236. Min Act: -0.1700
Data Index: 3949265 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.8611. Min Act: -0.1700
Data Index: 493402 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.8611. Min Act: -0.1700
Data Index: 2367431 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.9236. Min Act: -0.1700
Data Index: 4329441 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.7986. Min Act: -0.1700
Data Index: 3419928 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4861. Min Range: -8.4861
Max Act: 7.7986. Min Act: -0.1700
Data Index: 6290687 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19