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

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

Neuron 1637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4351. Min Range: -7.4351

Max Act: 7.4351. Min Act: -0.0000

Data Index: 939400 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 7.4351. Min Range: -7.4351

Max Act: 7.1611. Min Act: -0.0000

Data Index: 945683 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 7.4351. Min Range: -7.4351

Max Act: 6.7965. Min Act: -0.0000

Data Index: 13349 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 7.4351. Min Range: -7.4351

Max Act: 6.6170. Min Act: -0.0000

Data Index: 357129 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 7.4351. Min Range: -7.4351

Max Act: 6.5722. Min Act: -0.0000

Data Index: 24391 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 7.4351. Min Range: -7.4351

Max Act: 5.8920. Min Act: -0.0000

Data Index: 1330155 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 7.4351. Min Range: -7.4351

Max Act: 5.8079. Min Act: -0.0000

Data Index: 988942 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 7.4351. Min Range: -7.4351

Max Act: 5.8748. Min Act: -0.0000

Data Index: 107434 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 7.4351. Min Range: -7.4351

Max Act: 5.5085. Min Act: -0.0000

Data Index: 1123646 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 7.4351. Min Range: -7.4351

Max Act: 5.4751. Min Act: -0.0000

Data Index: 261631 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 7.4351. Min Range: -7.4351

Max Act: 5.3899. Min Act: -0.0000

Data Index: 70207 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 7.4351. Min Range: -7.4351

Max Act: 5.1940. Min Act: -0.0000

Data Index: 1359272 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 7.4351. Min Range: -7.4351

Max Act: 5.3189. Min Act: -0.0000

Data Index: 808546 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 7.4351. Min Range: -7.4351

Max Act: 5.2349. Min Act: -0.0000

Data Index: 1236253 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 7.4351. Min Range: -7.4351

Max Act: 4.9409. Min Act: -0.0000

Data Index: 800754 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 7.4351. Min Range: -7.4351

Max Act: 4.4601. Min Act: -0.0000

Data Index: 119271 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 7.4351. Min Range: -7.4351

Max Act: 4.6132. Min Act: -0.0000

Data Index: 864392 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 7.4351. Min Range: -7.4351

Max Act: 4.7450. Min Act: -0.0000

Data Index: 941633 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 7.4351. Min Range: -7.4351

Max Act: 4.7143. Min Act: -0.0000

Data Index: 96570 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 7.4351. Min Range: -7.4351

Max Act: 4.5534. Min Act: -0.0000

Data Index: 60516 (C4 (Web Text))

Max Activating Token Index: 573