Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2107 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1618. Min Act: -0.0002

Data Index: 966154 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1548. Min Act: -0.0002

Data Index: 232068 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1039325 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1513. Min Act: -0.0002

Data Index: 1205992 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1478. Min Act: -0.0002

Data Index: 10247 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1380. Min Act: -0.0001

Data Index: 81408 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1331. Min Act: -0.0002

Data Index: 81670 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1335. Min Act: -0.0002

Data Index: 1093123 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1270993 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1320. Min Act: -0.0002

Data Index: 3122 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1324. Min Act: -0.0001

Data Index: 216919 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1320330 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1324. Min Act: -0.0001

Data Index: 387300 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1272. Min Act: -0.0002

Data Index: 12678 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1234. Min Act: -0.0002

Data Index: 834452 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1010685 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1274. Min Act: -0.0002

Data Index: 1127217 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1264. Min Act: -0.0002

Data Index: 1159619 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1297. Min Act: -0.0002

Data Index: 393975 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1175929 (C4 (Web Text))

Max Activating Token Index: 492