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

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

Neuron 973 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: 0.0471. Min Range: -0.0471

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1341264 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1373918 (Python Code)

Max Activating Token Index: 594

Text #2

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1595148 (Python Code)

Max Activating Token Index: 714

Text #3

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1495263 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0404. Min Act: -0.0001

Data Index: 24719 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0377. Min Act: -0.0002

Data Index: 925146 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1541669 (Python Code)

Max Activating Token Index: 338

Text #7

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0364. Min Act: -0.0001

Data Index: 530901 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0346. Min Act: -0.0002

Data Index: 490854 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1529993 (Python Code)

Max Activating Token Index: 83

Text #10

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1350768 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0348. Min Act: -0.0002

Data Index: 773963 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0340. Min Act: -0.0002

Data Index: 966947 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0330. Min Act: -0.0002

Data Index: 714211 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1261971 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0328. Min Act: -0.0001

Data Index: 369298 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0330. Min Act: -0.0001

Data Index: 791354 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1434667 (Python Code)

Max Activating Token Index: 348

Text #18

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0342. Min Act: -0.0001

Data Index: 684619 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1245433 (C4 (Web Text))

Max Activating Token Index: 27