Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1404 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0345. Min Act: -0.0003

Data Index: 70565 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0342. Min Act: -0.0003

Data Index: 342275 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0313. Min Act: -0.0004

Data Index: 636956 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0323. Min Act: -0.0004

Data Index: 733297 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0316. Min Act: -0.0003

Data Index: 106453 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0308. Min Act: -0.0003

Data Index: 636806 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0299. Min Act: -0.0003

Data Index: 25869 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0303. Min Act: -0.0002

Data Index: 703094 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0304. Min Act: -0.0002

Data Index: 77324 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0304. Min Act: -0.0003

Data Index: 10441 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0297. Min Act: -0.0003

Data Index: 302821 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0300. Min Act: -0.0004

Data Index: 102949 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0304. Min Act: -0.0003

Data Index: 447475 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0298. Min Act: -0.0003

Data Index: 819461 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0302. Min Act: -0.0003

Data Index: 599769 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1045454 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1181661 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0286. Min Act: -0.0003

Data Index: 188748 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1327797 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0293. Min Act: -0.0003

Data Index: 538392 (C4 (Web Text))

Max Activating Token Index: 42