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

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

Neuron 1024 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: 0.0293. Min Range: -0.0293

Max Act: 0.0293. Min Act: -0.0002

Data Index: 699375 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1575667 (Python Code)

Max Activating Token Index: 693

Text #2

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0217. Min Act: -0.0001

Data Index: 797687 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1364473 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0203. Min Act: -0.0002

Data Index: 238553 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0214. Min Act: -0.0002

Data Index: 735652 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0199. Min Act: -0.0001

Data Index: 858513 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0204. Min Act: -0.0002

Data Index: 39268 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1573450 (Python Code)

Max Activating Token Index: 964

Text #9

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0193. Min Act: -0.0002

Data Index: 129618 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1318164 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0205. Min Act: -0.0001

Data Index: 922551 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0188. Min Act: -0.0002

Data Index: 732106 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1649026 (Python Code)

Max Activating Token Index: 762

Text #14

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0187. Min Act: -0.0001

Data Index: 273087 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1537018 (Python Code)

Max Activating Token Index: 292

Text #16

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0187. Min Act: -0.0002

Data Index: 683049 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1562760 (Python Code)

Max Activating Token Index: 140

Text #18

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1309618 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0184. Min Act: -0.0001

Data Index: 550751 (C4 (Web Text))

Max Activating Token Index: 247