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

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

Neuron 2134 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4067. Min Range: -2.4067

Max Act: 2.4067. Min Act: -0.0000

Data Index: 33905 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 2.4067. Min Range: -2.4067

Max Act: 2.4043. Min Act: -0.0000

Data Index: 754784 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 2.4067. Min Range: -2.4067

Max Act: 2.2616. Min Act: -0.0000

Data Index: 384197 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 2.4067. Min Range: -2.4067

Max Act: 2.1636. Min Act: -0.0000

Data Index: 173264 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.9439. Min Act: -0.0000

Data Index: 305218 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.9806. Min Act: -0.0000

Data Index: 717427 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.9075. Min Act: -0.0000

Data Index: 642254 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.9243. Min Act: -0.0000

Data Index: 451224 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.9832. Min Act: -0.0000

Data Index: 164086 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.8373. Min Act: -0.0000

Data Index: 265299 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.7586. Min Act: -0.0000

Data Index: 1280657 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.7927. Min Act: -0.0000

Data Index: 1118601 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.8207. Min Act: -0.0000

Data Index: 338836 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.7707. Min Act: -0.0000

Data Index: 726932 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.7649. Min Act: -0.0000

Data Index: 182869 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.8615. Min Act: -0.0000

Data Index: 1116053 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.8023. Min Act: -0.0000

Data Index: 527633 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.7792. Min Act: -0.0000

Data Index: 396618 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.7308. Min Act: -0.0000

Data Index: 292975 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 2.4067. Min Range: -2.4067

Max Act: 1.8241. Min Act: -0.0000

Data Index: 51540 (C4 (Web Text))

Max Activating Token Index: 659