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

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

Neuron 4162 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: 1.6599. Min Range: -1.6599

Max Act: 1.6599. Min Act: -0.0000

Data Index: 609192 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.5460. Min Act: -0.0000

Data Index: 671973 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1206637 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.4263. Min Act: -0.0000

Data Index: 745324 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.2377. Min Act: -0.0000

Data Index: 196179 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.2111. Min Act: -0.0000

Data Index: 459684 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.1175. Min Act: -0.0000

Data Index: 977768 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1103519 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.2491. Min Act: -0.0000

Data Index: 365320 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1024588 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.2125. Min Act: -0.0000

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.1651. Min Act: -0.0000

Data Index: 230147 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1273744 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.0712. Min Act: -0.0000

Data Index: 407824 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.6599. Min Range: -1.6599

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1347407 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.1602. Min Act: -0.0000

Data Index: 333338 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1209571 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 1.6599. Min Range: -1.6599

Max Act: 0.9571. Min Act: -0.0000

Data Index: 597791 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 1.6599. Min Range: -1.6599

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1354388 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 1.6599. Min Range: -1.6599

Max Act: 0.9709. Min Act: -0.0000

Data Index: 776683 (C4 (Web Text))

Max Activating Token Index: 746