Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3908 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.5460. Min Act: -0.0000

Data Index: 789095 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.5274. Min Act: -0.0000

Data Index: 559409 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4856. Min Act: -0.0000

Data Index: 848826 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4672. Min Act: -0.0000

Data Index: 646190 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4469. Min Act: -0.0000

Data Index: 851613 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4619. Min Act: -0.0000

Data Index: 797895 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1277018 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4175. Min Act: -0.0000

Data Index: 800023 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4421. Min Act: -0.0000

Data Index: 47646 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1344356 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4521. Min Act: -0.0000

Data Index: 984162 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1077946 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4385. Min Act: -0.0000

Data Index: 202578 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4237. Min Act: -0.0000

Data Index: 573901 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4251. Min Act: -0.0000

Data Index: 711210 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4177. Min Act: -0.0000

Data Index: 374598 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4490. Min Act: -0.0000

Data Index: 727285 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4303. Min Act: -0.0000

Data Index: 318167 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1190595 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.5460. Min Range: -0.5460

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1349181 (C4 (Web Text))

Max Activating Token Index: 639