Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2545 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3319. Min Act: -0.0001

Data Index: 1563982 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1400637 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2992. Min Act: -0.0000

Data Index: 50385 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1630060 (Python Code)

Max Activating Token Index: 774

Text #4

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2847. Min Act: -0.0001

Data Index: 160290 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2576. Min Act: -0.0001

Data Index: 1498655 (Python Code)

Max Activating Token Index: 696

Text #6

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2424. Min Act: -0.0000

Data Index: 350822 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2381. Min Act: -0.0000

Data Index: 363653 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2617. Min Act: -0.0000

Data Index: 344016 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2273. Min Act: -0.0000

Data Index: 669862 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2359. Min Act: -0.0000

Data Index: 543587 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2357. Min Act: -0.0001

Data Index: 255400 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2261. Min Act: -0.0001

Data Index: 1345201 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1330205 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1512211 (Python Code)

Max Activating Token Index: 821

Text #15

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2247. Min Act: -0.0000

Data Index: 24239 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2227. Min Act: -0.0001

Data Index: 796717 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2241. Min Act: -0.0001

Data Index: 254796 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2306. Min Act: -0.0001

Data Index: 666736 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1390204 (Python Code)

Max Activating Token Index: 395