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

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

Neuron 410 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: 0.1409. Min Range: -0.1409

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1558573 (Python Code)

Max Activating Token Index: 757

Text #1

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1481018 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1491761 (Python Code)

Max Activating Token Index: 163

Text #3

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1373557 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1251. Min Act: -0.0001

Data Index: 1163670 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1361498 (Python Code)

Max Activating Token Index: 135

Text #6

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1455968 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1284. Min Act: -0.0001

Data Index: 597890 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1393826 (Python Code)

Max Activating Token Index: 711

Text #9

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1558968 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1535986 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1251. Min Act: -0.0001

Data Index: 114500 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1624807 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1521844 (Python Code)

Max Activating Token Index: 403

Text #14

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1176. Min Act: -0.0001

Data Index: 933712 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1221. Min Act: -0.0001

Data Index: 522046 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1478974 (Python Code)

Max Activating Token Index: 896

Text #17

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1389622 (Python Code)

Max Activating Token Index: 94

Text #18

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1539861 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1398386 (Python Code)

Max Activating Token Index: 761