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

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

Neuron 535 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: 0.0408. Min Range: -0.0408

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1235387 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1165587 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0367. Min Act: -0.0003

Data Index: 534370 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0355. Min Act: -0.0003

Data Index: 518983 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0344. Min Act: -0.0003

Data Index: 930052 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1339203 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0343. Min Act: -0.0003

Data Index: 68080 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1084956 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0341. Min Act: -0.0003

Data Index: 215090 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1077876 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0322. Min Act: -0.0003

Data Index: 712704 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0327. Min Act: -0.0003

Data Index: 660634 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0308. Min Act: -0.0003

Data Index: 928900 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0305. Min Act: -0.0003

Data Index: 795465 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0302. Min Act: -0.0003

Data Index: 318834 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0308. Min Act: -0.0002

Data Index: 414300 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0302. Min Act: -0.0003

Data Index: 355430 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0307. Min Act: -0.0003

Data Index: 896011 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0299. Min Act: -0.0003

Data Index: 313648 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0304. Min Act: -0.0002

Data Index: 303214 (C4 (Web Text))

Max Activating Token Index: 883