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

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

Neuron 4488 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0000

Data Index: 462909 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1340595 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1061521 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0340. Min Act: -0.0000

Data Index: 556994 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0334. Min Act: -0.0000

Data Index: 641891 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0331. Min Act: -0.0000

Data Index: 683454 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0328. Min Act: -0.0000

Data Index: 409438 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0311. Min Act: -0.0000

Data Index: 169427 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0324. Min Act: -0.0001

Data Index: 341215 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0310. Min Act: -0.0000

Data Index: 259136 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0331. Min Act: -0.0000

Data Index: 1001911 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0328. Min Act: -0.0000

Data Index: 1153504 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1297442 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0294. Min Act: -0.0000

Data Index: 231475 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0304. Min Act: -0.0000

Data Index: 486853 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0280. Min Act: -0.0000

Data Index: 84597 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0292. Min Act: -0.0000

Data Index: 674855 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0303. Min Act: -0.0000

Data Index: 60516 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0289. Min Act: -0.0000

Data Index: 789748 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0282. Min Act: -0.0000

Data Index: 1142113 (C4 (Web Text))

Max Activating Token Index: 877