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

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

Neuron 5183 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2667. Min Act: -0.0001

Data Index: 1057176 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2296. Min Act: -0.0001

Data Index: 49556 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2469. Min Act: -0.0001

Data Index: 1027004 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2333. Min Act: -0.0001

Data Index: 940367 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2296. Min Act: -0.0001

Data Index: 1194456 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2257. Min Act: -0.0001

Data Index: 1197702 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2188. Min Act: -0.0001

Data Index: 683670 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2285. Min Act: -0.0001

Data Index: 698128 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2206. Min Act: -0.0001

Data Index: 1075802 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2074. Min Act: -0.0001

Data Index: 535664 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1967. Min Act: -0.0001

Data Index: 218650 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2019. Min Act: -0.0001

Data Index: 537249 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1882. Min Act: -0.0001

Data Index: 245046 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1974. Min Act: -0.0001

Data Index: 1321406 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1985. Min Act: -0.0001

Data Index: 18618 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2223. Min Act: -0.0001

Data Index: 779324 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1948. Min Act: -0.0001

Data Index: 646196 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1871. Min Act: -0.0001

Data Index: 374761 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1865. Min Act: -0.0001

Data Index: 270800 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1293909 (C4 (Web Text))

Max Activating Token Index: 723