Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3614 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1155161 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0477. Min Act: -0.0002

Data Index: 189568 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0412. Min Act: -0.0002

Data Index: 742282 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0395. Min Act: -0.0002

Data Index: 297719 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1283038 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0390. Min Act: -0.0002

Data Index: 541355 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0420. Min Act: -0.0002

Data Index: 319756 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0380. Min Act: -0.0002

Data Index: 286904 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0395. Min Act: -0.0002

Data Index: 753608 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0388. Min Act: -0.0002

Data Index: 59277 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0373. Min Act: -0.0002

Data Index: 338775 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0366. Min Act: -0.0002

Data Index: 802262 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0362. Min Act: -0.0002

Data Index: 234470 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1062741 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0338. Min Act: -0.0002

Data Index: 67271 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0326. Min Act: -0.0002

Data Index: 974525 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0339. Min Act: -0.0002

Data Index: 792939 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0343. Min Act: -0.0002

Data Index: 346824 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0318. Min Act: -0.0002

Data Index: 196577 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0316. Min Act: -0.0002

Data Index: 427316 (C4 (Web Text))

Max Activating Token Index: 116