Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2772 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0409. Min Act: -0.0001

Data Index: 294532 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0001

Data Index: 406577 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0380. Min Act: -0.0001

Data Index: 19674 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0387. Min Act: -0.0001

Data Index: 608552 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0386. Min Act: -0.0001

Data Index: 979996 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0366. Min Act: -0.0001

Data Index: 629557 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1545816 (Python Code)

Max Activating Token Index: 412

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0343. Min Act: -0.0001

Data Index: 808803 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1303393 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0346. Min Act: -0.0001

Data Index: 957058 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0324. Min Act: -0.0001

Data Index: 396570 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1253117 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1059248 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0315. Min Act: -0.0001

Data Index: 884826 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1113991 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0331. Min Act: -0.0001

Data Index: 155573 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1255214 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0320. Min Act: -0.0001

Data Index: 984516 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0326. Min Act: -0.0001

Data Index: 304533 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0325. Min Act: -0.0001

Data Index: 547970 (C4 (Web Text))

Max Activating Token Index: 532