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

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

Neuron 2598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0582. Min Range: -1.0582

Max Act: 1.0582. Min Act: -0.0000

Data Index: 8272 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.8017. Min Act: -0.0000

Data Index: 943964 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1108522 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1285744 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.7163. Min Act: -0.0000

Data Index: 289436 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.7268. Min Act: -0.0000

Data Index: 201267 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.7198. Min Act: -0.0000

Data Index: 376807 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.5605. Min Act: -0.0000

Data Index: 290641 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1030368 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1270950 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.6210. Min Act: -0.0000

Data Index: 975860 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1194224 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.6365. Min Act: -0.0000

Data Index: 38275 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.6474. Min Act: -0.0000

Data Index: 968933 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.6397. Min Act: -0.0000

Data Index: 28874 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.6542. Min Act: -0.0000

Data Index: 300991 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.5990. Min Act: -0.0000

Data Index: 276299 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1066831 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.6514. Min Act: -0.0000

Data Index: 568280 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.0582. Min Range: -1.0582

Max Act: 0.5936. Min Act: -0.0000

Data Index: 627278 (C4 (Web Text))

Max Activating Token Index: 605