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

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

Neuron 2513 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2482. Min Act: -0.0003

Data Index: 79185 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2480. Min Act: -0.0003

Data Index: 1642829 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2474. Min Act: -0.0003

Data Index: 611683 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2361. Min Act: -0.0003

Data Index: 1296737 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2760. Min Act: -0.0003

Data Index: 362926 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2170. Min Act: -0.0003

Data Index: 1757 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2640. Min Act: -0.0003

Data Index: 877118 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2289. Min Act: -0.0003

Data Index: 843924 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2141. Min Act: -0.0003

Data Index: 1553962 (Python Code)

Max Activating Token Index: 220

Text #9

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2286. Min Act: -0.0003

Data Index: 531658 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2039. Min Act: -0.0003

Data Index: 177393 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2355. Min Act: -0.0003

Data Index: 1624338 (Python Code)

Max Activating Token Index: 283

Text #12

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2267. Min Act: -0.0003

Data Index: 732878 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2245. Min Act: -0.0003

Data Index: 974890 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2248. Min Act: -0.0003

Data Index: 858096 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2169. Min Act: -0.0003

Data Index: 756480 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2503. Min Act: -0.0003

Data Index: 158852 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2174. Min Act: -0.0004

Data Index: 1151334 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2487. Min Act: -0.0003

Data Index: 248739 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2231. Min Act: -0.0003

Data Index: 1255467 (C4 (Web Text))

Max Activating Token Index: 539