Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4395 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.9299. Min Act: -0.0000

Data Index: 924661 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8616. Min Act: -0.0000

Data Index: 927041 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8797. Min Act: -0.0000

Data Index: 905939 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8364. Min Act: -0.0000

Data Index: 653694 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8054. Min Act: -0.0000

Data Index: 596094 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8346. Min Act: -0.0000

Data Index: 289359 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7834. Min Act: -0.0000

Data Index: 953028 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8275. Min Act: -0.0000

Data Index: 683640 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1158930 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7476. Min Act: -0.0000

Data Index: 210245 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7429. Min Act: -0.0000

Data Index: 131061 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7768. Min Act: -0.0000

Data Index: 900049 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1060158 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7768. Min Act: -0.0000

Data Index: 105289 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1220699 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7695. Min Act: -0.0000

Data Index: 755884 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7101. Min Act: -0.0000

Data Index: 256730 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6852. Min Act: -0.0000

Data Index: 521208 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7089. Min Act: -0.0000

Data Index: 981600 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1285150 (C4 (Web Text))

Max Activating Token Index: 471