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

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

Neuron 1894 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: 0.0289. Min Range: -0.0289

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1258459 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0273. Min Act: -0.0001

Data Index: 133819 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1415180 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0258. Min Act: -0.0000

Data Index: 718596 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0260. Min Act: -0.0000

Data Index: 970901 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1014310 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1290947 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0249. Min Act: -0.0001

Data Index: 607892 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0235. Min Act: -0.0001

Data Index: 107594 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1423355 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1211433 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1524378 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0241. Min Act: -0.0000

Data Index: 231644 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0233. Min Act: -0.0000

Data Index: 1293969 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0222. Min Act: -0.0000

Data Index: 476161 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1546872 (Python Code)

Max Activating Token Index: 858

Text #16

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0229. Min Act: -0.0000

Data Index: 1204011 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1237827 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1480456 (Python Code)

Max Activating Token Index: 362

Text #19

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0220. Min Act: -0.0000

Data Index: 195024 (C4 (Web Text))

Max Activating Token Index: 441