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

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

Neuron 3513 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: 1.9298. Min Range: -1.9298

Max Act: 1.9298. Min Act: -0.0001

Data Index: 862699 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.6957. Min Act: -0.0001

Data Index: 265085 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.4923. Min Act: -0.0001

Data Index: 276712 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.4296. Min Act: -0.0001

Data Index: 689010 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.3966. Min Act: -0.0001

Data Index: 219551 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.2335. Min Act: -0.0001

Data Index: 1046732 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.3176. Min Act: -0.0001

Data Index: 1114837 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.2445. Min Act: -0.0001

Data Index: 948609 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.3244. Min Act: -0.0001

Data Index: 497452 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.3202. Min Act: -0.0001

Data Index: 143929 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.2826. Min Act: -0.0001

Data Index: 1227458 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.2656. Min Act: -0.0001

Data Index: 1048539 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.3914. Min Act: -0.0001

Data Index: 391305 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.2867. Min Act: -0.0001

Data Index: 1314592 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.2635. Min Act: -0.0001

Data Index: 1296185 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.2278. Min Act: -0.0001

Data Index: 781869 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.2229. Min Act: -0.0001

Data Index: 1332411 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.1883. Min Act: -0.0001

Data Index: 458800 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.1846. Min Act: -0.0001

Data Index: 250528 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 1.9298. Min Range: -1.9298

Max Act: 1.2451. Min Act: -0.0001

Data Index: 574160 (C4 (Web Text))

Max Activating Token Index: 212