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

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

Neuron 2742 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1606. Min Act: -0.0000

Data Index: 730284 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1499. Min Act: -0.0000

Data Index: 229071 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1533. Min Act: -0.0000

Data Index: 510329 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1516672 (Python Code)

Max Activating Token Index: 541

Text #4

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1362. Min Act: -0.0000

Data Index: 960626 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1469. Min Act: -0.0000

Data Index: 895822 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1077726 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1401. Min Act: -0.0000

Data Index: 411604 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1193809 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1476. Min Act: -0.0000

Data Index: 981049 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1298. Min Act: -0.0000

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1304. Min Act: -0.0000

Data Index: 538257 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1261. Min Act: -0.0000

Data Index: 664038 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1257. Min Act: -0.0000

Data Index: 521397 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1210. Min Act: -0.0000

Data Index: 390381 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1127506 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1209. Min Act: -0.0000

Data Index: 184643 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1210. Min Act: -0.0000

Data Index: 95051 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1626163 (Python Code)

Max Activating Token Index: 704

Text #19

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1195. Min Act: -0.0000

Data Index: 155677 (C4 (Web Text))

Max Activating Token Index: 354