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

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

Neuron 4418 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0498. Min Act: -0.0001

Data Index: 337333 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0401. Min Act: -0.0001

Data Index: 616449 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0431. Min Act: -0.0001

Data Index: 314290 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1201251 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0410. Min Act: -0.0001

Data Index: 23531 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1039676 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1034977 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1020443 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0359. Min Act: -0.0001

Data Index: 786003 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1266564 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0311. Min Act: -0.0001

Data Index: 19318 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0335. Min Act: -0.0001

Data Index: 829740 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1248830 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0290. Min Act: -0.0001

Data Index: 337387 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0326. Min Act: -0.0001

Data Index: 305841 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0321. Min Act: -0.0001

Data Index: 996967 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0325. Min Act: -0.0001

Data Index: 32063 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0286. Min Act: -0.0001

Data Index: 53550 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0328. Min Act: -0.0001

Data Index: 765690 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0237. Min Act: -0.0001

Data Index: 160071 (C4 (Web Text))

Max Activating Token Index: 165