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

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

Neuron 315 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: 1.0346. Min Range: -1.0346

Max Act: 1.0346. Min Act: -0.0001

Data Index: 1085619 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9235. Min Act: -0.0001

Data Index: 64110 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.0346. Min Range: -1.0346

Max Act: 1.0147. Min Act: -0.0001

Data Index: 955331 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9185. Min Act: -0.0001

Data Index: 174788 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9910. Min Act: -0.0001

Data Index: 1201053 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9242. Min Act: -0.0001

Data Index: 947555 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9241. Min Act: -0.0001

Data Index: 1027432 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9232. Min Act: -0.0001

Data Index: 1321050 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7279. Min Act: -0.0001

Data Index: 673695 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9420. Min Act: -0.0001

Data Index: 1163580 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9293. Min Act: -0.0001

Data Index: 177889 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7528. Min Act: -0.0001

Data Index: 69264 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8984. Min Act: -0.0001

Data Index: 1126929 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8225. Min Act: -0.0001

Data Index: 960179 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8201. Min Act: -0.0001

Data Index: 719034 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7156. Min Act: -0.0001

Data Index: 316989 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8975. Min Act: -0.0001

Data Index: 790550 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8464. Min Act: -0.0001

Data Index: 302812 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7784. Min Act: -0.0001

Data Index: 1348439 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7493. Min Act: -0.0001

Data Index: 193914 (C4 (Web Text))

Max Activating Token Index: 694