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

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

Neuron 331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1469. Min Act: -0.0001

Data Index: 703416 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1625. Min Act: -0.0001

Data Index: 501099 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1291. Min Act: -0.0001

Data Index: 167238 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1332485 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1285. Min Act: -0.0001

Data Index: 248204 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1262511 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1257. Min Act: -0.0001

Data Index: 54876 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1275. Min Act: -0.0001

Data Index: 636850 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1267. Min Act: -0.0001

Data Index: 405865 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1220. Min Act: -0.0001

Data Index: 18985 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1307. Min Act: -0.0001

Data Index: 69366 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1292. Min Act: -0.0001

Data Index: 710059 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1024699 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1140946 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1225. Min Act: -0.0000

Data Index: 458668 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1281227 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1088. Min Act: -0.0001

Data Index: 722077 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1162. Min Act: -0.0001

Data Index: 231692 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1292472 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1234. Min Act: -0.0001

Data Index: 5944 (C4 (Web Text))

Max Activating Token Index: 117