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

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

Neuron 713 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1705. Min Act: -0.0001

Data Index: 1126512 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1610. Min Act: -0.0001

Data Index: 959570 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1538. Min Act: -0.0001

Data Index: 674911 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1522. Min Act: -0.0001

Data Index: 239551 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1417. Min Act: -0.0002

Data Index: 130225 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1443. Min Act: -0.0001

Data Index: 759712 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1379. Min Act: -0.0002

Data Index: 770662 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1312. Min Act: -0.0002

Data Index: 1015588 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1455. Min Act: -0.0001

Data Index: 368671 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1454. Min Act: -0.0002

Data Index: 488623 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1473. Min Act: -0.0002

Data Index: 1339089 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1434. Min Act: -0.0001

Data Index: 1142769 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1319. Min Act: -0.0002

Data Index: 691990 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1499. Min Act: -0.0002

Data Index: 1094603 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1402. Min Act: -0.0002

Data Index: 174788 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1234. Min Act: -0.0001

Data Index: 973908 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1091734 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1174. Min Act: -0.0001

Data Index: 454715 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1327. Min Act: -0.0001

Data Index: 214252 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.1705. Min Range: -0.1705

Max Act: 0.1272. Min Act: -0.0002

Data Index: 955316 (C4 (Web Text))

Max Activating Token Index: 320