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

Dataset: The Pile

Neuron 1616 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1505129 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1397. Min Act: -0.0000

Data Index: 47896 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1344. Min Act: -0.0000

Data Index: 941425 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1339. Min Act: -0.0000

Data Index: 978885 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1332. Min Act: -0.0000

Data Index: 249882 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1977185 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1325. Min Act: -0.0000

Data Index: 740639 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1855052 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1761304 (The Pile)

Max Activating Token Index: 399

Text #9

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1311. Min Act: -0.0000

Data Index: 363830 (The Pile)

Max Activating Token Index: 19

Text #10

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1023582 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1334. Min Act: -0.0000

Data Index: 530616 (The Pile)

Max Activating Token Index: 323

Text #12

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1423975 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1287. Min Act: -0.0000

Data Index: 540906 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1285. Min Act: -0.0000

Data Index: 174072 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1241. Min Act: -0.0000

Data Index: 399415 (The Pile)

Max Activating Token Index: 426

Text #16

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1275. Min Act: -0.0000

Data Index: 831640 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1271. Min Act: -0.0000

Data Index: 272146 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1313. Min Act: -0.0000

Data Index: 209240 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1270. Min Act: -0.0000

Data Index: 482142 (The Pile)

Max Activating Token Index: 292