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

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

Neuron 1817 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0570. Min Range: -1.0570

Max Act: 1.0079. Min Act: -0.0001

Data Index: 371406 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 1.0570. Min Range: -1.0570

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1018093 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.0570. Min Range: -1.0570

Max Act: 1.0570. Min Act: -0.0001

Data Index: 1045550 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1319281 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9619. Min Act: -0.0001

Data Index: 1122109 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1222237 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9522. Min Act: -0.0001

Data Index: 873565 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1195413 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8811. Min Act: -0.0000

Data Index: 949534 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8482. Min Act: -0.0000

Data Index: 267308 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8730. Min Act: -0.0001

Data Index: 137252 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8983. Min Act: -0.0000

Data Index: 776448 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9095. Min Act: -0.0001

Data Index: 1091006 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1162194 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8103. Min Act: -0.0001

Data Index: 1221859 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8307. Min Act: -0.0000

Data Index: 44978 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8427. Min Act: -0.0001

Data Index: 795988 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8222. Min Act: -0.0001

Data Index: 440210 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7926. Min Act: -0.0001

Data Index: 846274 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8367. Min Act: -0.0001

Data Index: 1354892 (C4 (Web Text))

Max Activating Token Index: 393