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

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

Neuron 2247 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: 0.2700. Min Range: -0.2700

Max Act: 0.2482. Min Act: -0.0001

Data Index: 1198269 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2700. Min Act: -0.0001

Data Index: 175891 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2572. Min Act: -0.0001

Data Index: 568248 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2444. Min Act: -0.0001

Data Index: 34689 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2370. Min Act: -0.0001

Data Index: 354443 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2441. Min Act: -0.0001

Data Index: 469206 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2341. Min Act: -0.0001

Data Index: 1322833 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2386. Min Act: -0.0001

Data Index: 361660 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2356. Min Act: -0.0001

Data Index: 554194 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2415. Min Act: -0.0001

Data Index: 375893 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2229. Min Act: -0.0001

Data Index: 828934 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2299. Min Act: -0.0001

Data Index: 901622 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2293. Min Act: -0.0001

Data Index: 717130 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2284. Min Act: -0.0001

Data Index: 410666 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2368. Min Act: -0.0001

Data Index: 26419 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2256. Min Act: -0.0001

Data Index: 1166830 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2179. Min Act: -0.0001

Data Index: 188540 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2321. Min Act: -0.0001

Data Index: 491721 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2243. Min Act: -0.0001

Data Index: 780912 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2226. Min Act: -0.0001

Data Index: 472214 (C4 (Web Text))

Max Activating Token Index: 706