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

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

Neuron 22 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1500. Min Act: -0.0000

Data Index: 724237 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1533. Min Act: -0.0001

Data Index: 452481 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1501. Min Act: -0.0001

Data Index: 198807 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1502. Min Act: -0.0000

Data Index: 872944 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1247. Min Act: -0.0001

Data Index: 442714 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1490. Min Act: -0.0001

Data Index: 264748 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1383. Min Act: -0.0001

Data Index: 681703 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1422. Min Act: -0.0000

Data Index: 67509 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1372. Min Act: -0.0000

Data Index: 411051 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1127471 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1446. Min Act: -0.0001

Data Index: 476777 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1349. Min Act: -0.0001

Data Index: 53 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1317030 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1064211 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1320. Min Act: -0.0000

Data Index: 743693 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1372. Min Act: -0.0001

Data Index: 661539 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1185084 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1373. Min Act: -0.0001

Data Index: 895735 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1327. Min Act: -0.0000

Data Index: 19067 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1227. Min Act: -0.0000

Data Index: 252641 (C4 (Web Text))

Max Activating Token Index: 375