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

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

Neuron 2708 in Layer 5

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: -0.0000

Data Index: 1338657 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0448. Min Act: -0.0000

Data Index: 134148 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0426. Min Act: -0.0000

Data Index: 111172 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0396. Min Act: -0.0000

Data Index: 1583677 (Python Code)

Max Activating Token Index: 962

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0420. Min Act: -0.0000

Data Index: 748044 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0416. Min Act: -0.0000

Data Index: 811429 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0421. Min Act: -0.0000

Data Index: 868086 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0374. Min Act: -0.0000

Data Index: 361802 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0422. Min Act: -0.0000

Data Index: 476593 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0385. Min Act: -0.0000

Data Index: 60044 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0398. Min Act: -0.0000

Data Index: 360553 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1350090 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0383. Min Act: -0.0000

Data Index: 623221 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1028199 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0392. Min Act: -0.0000

Data Index: 521884 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0332. Min Act: -0.0000

Data Index: 1459654 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1014438 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0345. Min Act: -0.0000

Data Index: 349564 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0361. Min Act: -0.0000

Data Index: 665371 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1485195 (Python Code)

Max Activating Token Index: 617