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

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

Neuron 4792 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: 0.6471. Min Range: -0.6471

Max Act: 0.6471. Min Act: -0.0000

Data Index: 598231 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1300449 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1397524 (Python Code)

Max Activating Token Index: 872

Text #3

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5145. Min Act: -0.0000

Data Index: 809964 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4877. Min Act: -0.0000

Data Index: 292807 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4961. Min Act: -0.0000

Data Index: 316269 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4750. Min Act: -0.0000

Data Index: 392916 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1233162 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4361. Min Act: -0.0000

Data Index: 985578 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1400860 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1217078 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1448767 (Python Code)

Max Activating Token Index: 895

Text #12

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4318. Min Act: -0.0000

Data Index: 802152 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4061. Min Act: -0.0000

Data Index: 344325 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4272. Min Act: -0.0000

Data Index: 917190 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4421. Min Act: -0.0000

Data Index: 342542 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4452. Min Act: -0.0000

Data Index: 23700 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4338. Min Act: -0.0000

Data Index: 622907 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1272889 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4505. Min Act: -0.0000

Data Index: 656558 (C4 (Web Text))

Max Activating Token Index: 712