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

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

Neuron 1711 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1436. Min Act: -0.0001

Data Index: 364703 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1347. Min Act: -0.0001

Data Index: 577287 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1212253 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1358. Min Act: -0.0001

Data Index: 607828 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1308. Min Act: -0.0001

Data Index: 649038 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1300. Min Act: -0.0001

Data Index: 456524 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1269. Min Act: -0.0001

Data Index: 937760 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1313. Min Act: -0.0001

Data Index: 293573 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1204. Min Act: -0.0001

Data Index: 718381 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1241. Min Act: -0.0001

Data Index: 943544 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1271. Min Act: -0.0001

Data Index: 923707 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1317. Min Act: -0.0001

Data Index: 544836 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1131. Min Act: -0.0001

Data Index: 157785 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1222. Min Act: -0.0001

Data Index: 361649 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1253. Min Act: -0.0001

Data Index: 725357 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1204. Min Act: -0.0001

Data Index: 109904 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1020242 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1014. Min Act: -0.0001

Data Index: 599773 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1356176 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1201467 (C4 (Web Text))

Max Activating Token Index: 437