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

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

Neuron 2300 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1403. Min Act: -0.0002

Data Index: 168327 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1445. Min Act: -0.0002

Data Index: 1225276 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1250. Min Act: -0.0002

Data Index: 11933 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1266. Min Act: -0.0002

Data Index: 258206 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1303. Min Act: -0.0002

Data Index: 1265229 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1299. Min Act: -0.0002

Data Index: 1066210 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1343. Min Act: -0.0002

Data Index: 1093647 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1314. Min Act: -0.0002

Data Index: 597278 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1312. Min Act: -0.0002

Data Index: 153813 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1269. Min Act: -0.0002

Data Index: 896394 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1302. Min Act: -0.0002

Data Index: 758716 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1320. Min Act: -0.0002

Data Index: 522647 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1232. Min Act: -0.0002

Data Index: 567458 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1275. Min Act: -0.0002

Data Index: 278536 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1229. Min Act: -0.0002

Data Index: 839590 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1049275 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1264. Min Act: -0.0002

Data Index: 381838 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1227. Min Act: -0.0002

Data Index: 602169 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1249. Min Act: -0.0002

Data Index: 630040 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1251. Min Act: -0.0002

Data Index: 687862 (C4 (Web Text))

Max Activating Token Index: 50