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

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

Neuron 4434 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0707. Min Act: -0.0003

Data Index: 518145 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0610. Min Act: -0.0003

Data Index: 54974 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0599. Min Act: -0.0003

Data Index: 173499 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0584. Min Act: -0.0003

Data Index: 365095 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0599. Min Act: -0.0003

Data Index: 891566 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0578. Min Act: -0.0003

Data Index: 159132 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0529. Min Act: -0.0003

Data Index: 649933 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0529. Min Act: -0.0003

Data Index: 20345 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0509. Min Act: -0.0003

Data Index: 413263 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1257787 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0514. Min Act: -0.0003

Data Index: 859719 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0509. Min Act: -0.0003

Data Index: 251069 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0506. Min Act: -0.0003

Data Index: 245423 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0503. Min Act: -0.0003

Data Index: 733418 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1278645 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0489. Min Act: -0.0003

Data Index: 609047 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0489. Min Act: -0.0003

Data Index: 467148 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0482. Min Act: -0.0003

Data Index: 942628 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0494. Min Act: -0.0003

Data Index: 92346 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1207274 (C4 (Web Text))

Max Activating Token Index: 46