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

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

Neuron 3805 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0001

Data Index: 988839 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1480. Min Act: -0.0001

Data Index: 202400 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1344848 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1344788 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1506. Min Act: -0.0001

Data Index: 430856 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1401. Min Act: -0.0001

Data Index: 679256 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1133252 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1352. Min Act: -0.0001

Data Index: 560810 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1312. Min Act: -0.0001

Data Index: 473917 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1179436 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1272. Min Act: -0.0001

Data Index: 36514 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1356. Min Act: -0.0001

Data Index: 193965 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1204797 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1057305 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1190. Min Act: -0.0001

Data Index: 62347 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1167. Min Act: -0.0001

Data Index: 424744 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1162. Min Act: -0.0001

Data Index: 722474 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1184. Min Act: -0.0001

Data Index: 903131 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1125. Min Act: -0.0001

Data Index: 597001 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1161. Min Act: -0.0001

Data Index: 306992 (C4 (Web Text))

Max Activating Token Index: 848