Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.8553. Min Act: -0.1700
Data Index: 5832338 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.8240. Min Act: -0.1700
Data Index: 4358902 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.7928. Min Act: -0.1700
Data Index: 6870343 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.7615. Min Act: -0.1700
Data Index: 2492913 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.7146. Min Act: -0.1700
Data Index: 901181 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.7146. Min Act: -0.1700
Data Index: 209441 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.7302. Min Act: -0.1700
Data Index: 2899773 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6989. Min Act: -0.1700
Data Index: 3626929 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6989. Min Act: -0.1700
Data Index: 7010519 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6833. Min Act: -0.1700
Data Index: 1715330 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6989. Min Act: -0.1700
Data Index: 8390742 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6833. Min Act: -0.1700
Data Index: 447622 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6520. Min Act: -0.1700
Data Index: 433233 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6520. Min Act: -0.1700
Data Index: 472890 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6520. Min Act: -0.1700
Data Index: 2632203 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6363. Min Act: -0.1700
Data Index: 3002072 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6363. Min Act: -0.1700
Data Index: 6736512 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6363. Min Act: -0.1700
Data Index: 3717367 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6363. Min Act: -0.1700
Data Index: 1174584 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8553. Min Range: -3.8553
Max Act: 3.6207. Min Act: -0.1700
Data Index: 2479010 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19