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

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

Neuron 390 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.7113. Min Act: -0.0001

Data Index: 577948 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.7420. Min Act: -0.0001

Data Index: 1274237 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.7190. Min Act: -0.0002

Data Index: 794958 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.7251. Min Act: -0.0001

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6003. Min Act: -0.0001

Data Index: 868718 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.7335. Min Act: -0.0001

Data Index: 1302443 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6283. Min Act: -0.0001

Data Index: 441852 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6435. Min Act: -0.0001

Data Index: 1228802 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.7100. Min Act: -0.0001

Data Index: 985346 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6347. Min Act: -0.0001

Data Index: 230729 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6247. Min Act: -0.0001

Data Index: 622938 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5768. Min Act: -0.0001

Data Index: 958441 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6373. Min Act: -0.0001

Data Index: 162044 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6530. Min Act: -0.0001

Data Index: 71384 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6486. Min Act: -0.0001

Data Index: 1256553 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6263. Min Act: -0.0001

Data Index: 615454 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6195. Min Act: -0.0001

Data Index: 291385 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6552. Min Act: -0.0001

Data Index: 105725 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6243. Min Act: -0.0001

Data Index: 1289457 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5840. Min Act: -0.0001

Data Index: 133903 (C4 (Web Text))

Max Activating Token Index: 582