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

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

Neuron 1875 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: 1.6791. Min Range: -1.6791

Max Act: 1.6791. Min Act: -0.0000

Data Index: 729675 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.4342. Min Act: -0.0001

Data Index: 1228223 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.3243. Min Act: -0.0000

Data Index: 995249 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.2513. Min Act: -0.0000

Data Index: 299618 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1063028 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.2138. Min Act: -0.0001

Data Index: 631594 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.2432. Min Act: -0.0000

Data Index: 956215 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.1298. Min Act: -0.0000

Data Index: 926184 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1195087 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.0627. Min Act: -0.0001

Data Index: 466808 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.1317. Min Act: -0.0001

Data Index: 1162625 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.1290. Min Act: -0.0001

Data Index: 499232 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.1227. Min Act: -0.0001

Data Index: 878375 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.0639. Min Act: -0.0000

Data Index: 354526 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.0613. Min Act: -0.0000

Data Index: 742708 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.0786. Min Act: -0.0000

Data Index: 964781 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.0248. Min Act: -0.0001

Data Index: 1312767 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.0602. Min Act: -0.0001

Data Index: 30973 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.6791. Min Range: -1.6791

Max Act: 0.9937. Min Act: -0.0000

Data Index: 166600 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 1.6791. Min Range: -1.6791

Max Act: 1.0184. Min Act: -0.0001

Data Index: 456326 (C4 (Web Text))

Max Activating Token Index: 535