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

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

Neuron 4441 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0520. Min Act: -0.0002

Data Index: 74985 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0472. Min Act: -0.0002

Data Index: 257975 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0418. Min Act: -0.0002

Data Index: 147366 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0388. Min Act: -0.0002

Data Index: 493754 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0383. Min Act: -0.0002

Data Index: 892199 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1323048 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1118207 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0376. Min Act: -0.0002

Data Index: 302667 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1317310 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0377. Min Act: -0.0002

Data Index: 569312 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0405. Min Act: -0.0002

Data Index: 247698 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1087993 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0387. Min Act: -0.0002

Data Index: 882568 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1015077 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0397. Min Act: -0.0002

Data Index: 96394 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0411. Min Act: -0.0002

Data Index: 676958 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0411. Min Act: -0.0002

Data Index: 424091 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1172103 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0360. Min Act: -0.0002

Data Index: 351737 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0335. Min Act: -0.0002

Data Index: 641032 (C4 (Web Text))

Max Activating Token Index: 208