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

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

Neuron 2897 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1796. Min Act: -0.0000

Data Index: 588407 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1854. Min Act: -0.0000

Data Index: 137140 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1595. Min Act: -0.0000

Data Index: 323423 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1626. Min Act: -0.0000

Data Index: 495219 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1341197 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1057495 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1175843 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1082475 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1033065 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1325. Min Act: -0.0000

Data Index: 113821 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1383. Min Act: -0.0000

Data Index: 965997 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1305. Min Act: -0.0000

Data Index: 235381 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1248. Min Act: -0.0000

Data Index: 92626 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1221. Min Act: -0.0000

Data Index: 956316 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1316. Min Act: -0.0000

Data Index: 760821 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1339550 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1204. Min Act: -0.0000

Data Index: 748100 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1010560 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1157. Min Act: -0.0000

Data Index: 722940 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1197575 (C4 (Web Text))

Max Activating Token Index: 541