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

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

Neuron 899 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.2334. Min Act: -0.0000

Data Index: 531602 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.2106. Min Act: -0.0001

Data Index: 186636 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1096495 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1863. Min Act: -0.0001

Data Index: 428180 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1794. Min Act: -0.0000

Data Index: 710297 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1581. Min Act: -0.0001

Data Index: 996230 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1634. Min Act: -0.0000

Data Index: 414398 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1213725 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1656. Min Act: -0.0000

Data Index: 438770 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1599. Min Act: -0.0000

Data Index: 616960 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1485. Min Act: -0.0000

Data Index: 830096 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1193212 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1417. Min Act: -0.0001

Data Index: 1474711 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1296. Min Act: -0.0001

Data Index: 599459 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1320. Min Act: -0.0001

Data Index: 447231 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1548264 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1243. Min Act: -0.0001

Data Index: 454193 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1423. Min Act: -0.0000

Data Index: 159195 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1161671 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1299. Min Act: -0.0000

Data Index: 376883 (C4 (Web Text))

Max Activating Token Index: 955