Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 560 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1532. Min Act: -0.0002

Data Index: 706730 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1480. Min Act: -0.0002

Data Index: 614532 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1461. Min Act: -0.0002

Data Index: 1068760 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1455. Min Act: -0.0002

Data Index: 943919 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1374. Min Act: -0.0002

Data Index: 723984 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1321. Min Act: -0.0002

Data Index: 590354 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1384. Min Act: -0.0002

Data Index: 1286735 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1319. Min Act: -0.0001

Data Index: 877443 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1242. Min Act: -0.0001

Data Index: 136123 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1357533 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1249. Min Act: -0.0002

Data Index: 764279 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1279. Min Act: -0.0002

Data Index: 814007 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1198870 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1204. Min Act: -0.0002

Data Index: 1068063 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1200. Min Act: -0.0002

Data Index: 736343 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1242. Min Act: -0.0001

Data Index: 188963 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1257. Min Act: -0.0002

Data Index: 97906 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1194. Min Act: -0.0002

Data Index: 406200 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1175. Min Act: -0.0002

Data Index: 570758 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1135. Min Act: -0.0002

Data Index: 67799 (C4 (Web Text))

Max Activating Token Index: 981