Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4986 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.4238. Min Act: -0.0000

Data Index: 329487 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.4170. Min Act: -0.0000

Data Index: 360632 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3540. Min Act: -0.0000

Data Index: 715855 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2798. Min Act: -0.0000

Data Index: 352228 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1426715 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2319. Min Act: -0.0000

Data Index: 226007 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2283. Min Act: -0.0000

Data Index: 530868 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1478433 (Python Code)

Max Activating Token Index: 439

Text #8

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1334854 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2188. Min Act: -0.0000

Data Index: 126527 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2107. Min Act: -0.0000

Data Index: 363932 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1253965 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1148648 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1067546 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1436243 (Python Code)

Max Activating Token Index: 119

Text #15

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1642. Min Act: -0.0000

Data Index: 545378 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1071533 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1628. Min Act: -0.0000

Data Index: 718910 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1241086 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1720. Min Act: -0.0000

Data Index: 795674 (C4 (Web Text))

Max Activating Token Index: 733