Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1753 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0005

Data Index: 959513 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0361. Min Act: -0.0005

Data Index: 804946 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0364. Min Act: -0.0005

Data Index: 63055 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0361. Min Act: -0.0005

Data Index: 1062117 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0335. Min Act: -0.0005

Data Index: 503970 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0334. Min Act: -0.0005

Data Index: 355991 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0326. Min Act: -0.0005

Data Index: 1151611 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0337. Min Act: -0.0005

Data Index: 682272 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0321. Min Act: -0.0005

Data Index: 169737 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0321. Min Act: -0.0005

Data Index: 1232663 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0313. Min Act: -0.0005

Data Index: 605341 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0326. Min Act: -0.0005

Data Index: 481770 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0327. Min Act: -0.0005

Data Index: 466603 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0324. Min Act: -0.0005

Data Index: 119065 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0322. Min Act: -0.0005

Data Index: 985235 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0331. Min Act: -0.0005

Data Index: 93445 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0323. Min Act: -0.0005

Data Index: 346464 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0305. Min Act: -0.0005

Data Index: 833354 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0314. Min Act: -0.0005

Data Index: 860609 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0319. Min Act: -0.0005

Data Index: 1036624 (C4 (Web Text))

Max Activating Token Index: 709