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

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

Neuron 4744 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: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0002

Data Index: 27110 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1017200 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0372. Min Act: -0.0002

Data Index: 370440 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1522745 (Python Code)

Max Activating Token Index: 833

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0337. Min Act: -0.0002

Data Index: 592248 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0342. Min Act: -0.0002

Data Index: 170020 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1446453 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0337. Min Act: -0.0002

Data Index: 329091 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1320189 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0324. Min Act: -0.0002

Data Index: 278593 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1488642 (Python Code)

Max Activating Token Index: 958

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0325. Min Act: -0.0002

Data Index: 727535 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0330. Min Act: -0.0002

Data Index: 144905 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0328. Min Act: -0.0002

Data Index: 610887 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1426679 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0315. Min Act: -0.0002

Data Index: 499098 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0318. Min Act: -0.0002

Data Index: 205451 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0323. Min Act: -0.0002

Data Index: 580079 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1141112 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0319. Min Act: -0.0002

Data Index: 63388 (C4 (Web Text))

Max Activating Token Index: 452