Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2730 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0506. Min Act: -0.0001

Data Index: 156564 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0541. Min Act: -0.0002

Data Index: 945319 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0445. Min Act: -0.0001

Data Index: 417543 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1252832 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0369. Min Act: -0.0001

Data Index: 550852 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0365. Min Act: -0.0001

Data Index: 994046 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0356. Min Act: -0.0001

Data Index: 176975 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1263194 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0340. Min Act: -0.0001

Data Index: 495617 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0329. Min Act: -0.0001

Data Index: 513002 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0306. Min Act: -0.0001

Data Index: 738187 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1357506 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1328643 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1233356 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0322. Min Act: -0.0001

Data Index: 996841 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0300. Min Act: -0.0001

Data Index: 573633 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0317. Min Act: -0.0001

Data Index: 245893 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0323. Min Act: -0.0001

Data Index: 281183 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0323. Min Act: -0.0001

Data Index: 654315 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0315. Min Act: -0.0001

Data Index: 417639 (C4 (Web Text))

Max Activating Token Index: 7