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

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

Neuron 2572 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: 1.4059. Min Range: -1.4059

Max Act: 1.4059. Min Act: -0.0001

Data Index: 380280 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.3622. Min Act: -0.0000

Data Index: 73537 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.3990. Min Act: -0.0001

Data Index: 124207 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.1246. Min Act: -0.0001

Data Index: 264760 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0875. Min Act: -0.0000

Data Index: 290402 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.2126. Min Act: -0.0001

Data Index: 1302705 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0855. Min Act: -0.0001

Data Index: 535776 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0816. Min Act: -0.0001

Data Index: 226780 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.1039. Min Act: -0.0001

Data Index: 167881 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0004. Min Act: -0.0001

Data Index: 378564 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.1293. Min Act: -0.0001

Data Index: 224097 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0539. Min Act: -0.0001

Data Index: 870498 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.9221. Min Act: -0.0000

Data Index: 978225 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0387. Min Act: -0.0001

Data Index: 766502 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.9846. Min Act: -0.0001

Data Index: 1307769 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0322. Min Act: -0.0001

Data Index: 60752 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0298. Min Act: -0.0001

Data Index: 420737 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0183. Min Act: -0.0001

Data Index: 830691 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0765. Min Act: -0.0001

Data Index: 922003 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0041. Min Act: -0.0001

Data Index: 7189 (C4 (Web Text))

Max Activating Token Index: 1001