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

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

Neuron 2140 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: 0.1539. Min Range: -0.1539

Max Act: 0.1480. Min Act: -0.0001

Data Index: 483238 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1539. Min Act: -0.0001

Data Index: 676442 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1424. Min Act: -0.0001

Data Index: 839947 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1365. Min Act: -0.0001

Data Index: 433548 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1299. Min Act: -0.0001

Data Index: 247233 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1081249 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1168352 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1245. Min Act: -0.0001

Data Index: 612799 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1237. Min Act: -0.0001

Data Index: 392324 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1283. Min Act: -0.0001

Data Index: 281900 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1220. Min Act: -0.0001

Data Index: 518549 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1222. Min Act: -0.0001

Data Index: 987512 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1174. Min Act: -0.0001

Data Index: 557488 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1165. Min Act: -0.0001

Data Index: 229328 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1263. Min Act: -0.0001

Data Index: 141082 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1208. Min Act: -0.0001

Data Index: 178222 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1155. Min Act: -0.0001

Data Index: 400614 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1194. Min Act: -0.0001

Data Index: 256822 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1104. Min Act: -0.0001

Data Index: 527229 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1087. Min Act: -0.0001

Data Index: 487579 (C4 (Web Text))

Max Activating Token Index: 545