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

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

Neuron 3513 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: 0.0461. Min Range: -0.0461

Max Act: 0.0461. Min Act: -0.0002

Data Index: 481579 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1330268 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0422. Min Act: -0.0002

Data Index: 624884 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1326363 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1033203 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1416744 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0331. Min Act: -0.0002

Data Index: 20173 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1274801 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1509608 (Python Code)

Max Activating Token Index: 237

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0344. Min Act: -0.0002

Data Index: 560466 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1534674 (Python Code)

Max Activating Token Index: 465

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0357. Min Act: -0.0003

Data Index: 225459 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1519022 (Python Code)

Max Activating Token Index: 408

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1323355 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1597708 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0302. Min Act: -0.0002

Data Index: 176438 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0324. Min Act: -0.0002

Data Index: 56337 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0293. Min Act: -0.0003

Data Index: 897504 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1172275 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1579884 (Python Code)

Max Activating Token Index: 469