Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4125 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0349. Min Act: -0.0002

Data Index: 503830 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1190189 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1098024 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0292. Min Act: -0.0002

Data Index: 675350 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0270. Min Act: -0.0002

Data Index: 208202 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0318. Min Act: -0.0002

Data Index: 554019 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1088291 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0267. Min Act: -0.0002

Data Index: 822211 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1164927 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0262. Min Act: -0.0002

Data Index: 579683 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1195950 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0261. Min Act: -0.0002

Data Index: 655241 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0256. Min Act: -0.0002

Data Index: 644184 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0255. Min Act: -0.0002

Data Index: 567926 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1069305 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0241. Min Act: -0.0002

Data Index: 565937 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0260. Min Act: -0.0002

Data Index: 382737 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0251. Min Act: -0.0002

Data Index: 118982 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0237. Min Act: -0.0002

Data Index: 767705 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0231. Min Act: -0.0002

Data Index: 201201 (C4 (Web Text))

Max Activating Token Index: 212