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

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

Neuron 2256 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0247. Min Act: -0.0000

Data Index: 283986 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0231. Min Act: -0.0000

Data Index: 458440 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0220. Min Act: -0.0001

Data Index: 735818 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0234. Min Act: -0.0000

Data Index: 83384 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0218. Min Act: -0.0001

Data Index: 945797 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0214. Min Act: -0.0000

Data Index: 1125863 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0207. Min Act: -0.0000

Data Index: 1251561 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0209. Min Act: -0.0000

Data Index: 1199037 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0214. Min Act: -0.0001

Data Index: 833342 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0207. Min Act: -0.0000

Data Index: 1180906 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0200. Min Act: -0.0000

Data Index: 1270025 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0210. Min Act: -0.0000

Data Index: 363289 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0209. Min Act: -0.0000

Data Index: 1257527 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0204. Min Act: -0.0001

Data Index: 673639 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0207. Min Act: -0.0000

Data Index: 929646 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0225. Min Act: -0.0001

Data Index: 705004 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0198. Min Act: -0.0000

Data Index: 308857 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0187. Min Act: -0.0001

Data Index: 265702 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0201. Min Act: -0.0000

Data Index: 1233942 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0194. Min Act: -0.0000

Data Index: 603073 (C4 (Web Text))

Max Activating Token Index: 742