Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2677 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.5604. Min Act: -0.0001

Data Index: 403133 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.5262. Min Act: -0.0001

Data Index: 622447 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4575. Min Act: -0.0001

Data Index: 1280322 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4613. Min Act: -0.0001

Data Index: 155308 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3621. Min Act: -0.0001

Data Index: 883828 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3567. Min Act: -0.0001

Data Index: 483077 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3105. Min Act: -0.0001

Data Index: 703615 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3855. Min Act: -0.0001

Data Index: 25656 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3437. Min Act: -0.0001

Data Index: 358441 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3095. Min Act: -0.0001

Data Index: 970228 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2243. Min Act: -0.0001

Data Index: 600173 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3169. Min Act: -0.0001

Data Index: 1309595 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3219. Min Act: -0.0001

Data Index: 828209 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2311. Min Act: -0.0001

Data Index: 894734 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2074. Min Act: -0.0001

Data Index: 595861 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2429. Min Act: -0.0001

Data Index: 615843 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.1321. Min Act: -0.0001

Data Index: 818489 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2367. Min Act: -0.0001

Data Index: 662635 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.1635. Min Act: -0.0001

Data Index: 954299 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.0980. Min Act: -0.0001

Data Index: 804949 (C4 (Web Text))

Max Activating Token Index: 645