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

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

Neuron 1166 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2645. Min Act: -0.0003

Data Index: 828483 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2429. Min Act: -0.0003

Data Index: 1004889 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2481. Min Act: -0.0003

Data Index: 26435 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2404. Min Act: -0.0003

Data Index: 93876 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2544. Min Act: -0.0003

Data Index: 110025 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2360. Min Act: -0.0003

Data Index: 518945 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2484. Min Act: -0.0003

Data Index: 919568 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2286. Min Act: -0.0003

Data Index: 373971 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2202. Min Act: -0.0003

Data Index: 454820 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2351. Min Act: -0.0003

Data Index: 876200 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2184. Min Act: -0.0003

Data Index: 82213 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2415. Min Act: -0.0003

Data Index: 1277407 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2237. Min Act: -0.0003

Data Index: 225270 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2156. Min Act: -0.0003

Data Index: 136350 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2269. Min Act: -0.0003

Data Index: 546887 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2137. Min Act: -0.0003

Data Index: 1102886 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2212. Min Act: -0.0003

Data Index: 122090 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2354. Min Act: -0.0003

Data Index: 98553 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2177. Min Act: -0.0003

Data Index: 1144715 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2241. Min Act: -0.0003

Data Index: 47832 (C4 (Web Text))

Max Activating Token Index: 975