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

Dataset: The Pile

Neuron 4624 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.2092. Min Range: -10.2092

Max Act: 10.0581. Min Act: -0.0000

Data Index: 1615461 (The Pile)

Max Activating Token Index: 783

Text #1

Max Range: 10.2092. Min Range: -10.2092

Max Act: 10.2092. Min Act: -0.0000

Data Index: 732732 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 10.2092. Min Range: -10.2092

Max Act: 9.6619. Min Act: -0.0000

Data Index: 973654 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 10.2092. Min Range: -10.2092

Max Act: 9.8158. Min Act: -0.0000

Data Index: 1852354 (The Pile)

Max Activating Token Index: 658

Text #4

Max Range: 10.2092. Min Range: -10.2092

Max Act: 9.7037. Min Act: -0.0000

Data Index: 1998524 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 10.2092. Min Range: -10.2092

Max Act: 9.5277. Min Act: -0.0000

Data Index: 1720897 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 10.2092. Min Range: -10.2092

Max Act: 9.1403. Min Act: -0.0000

Data Index: 1247486 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 10.2092. Min Range: -10.2092

Max Act: 9.3767. Min Act: -0.0000

Data Index: 1749576 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 10.2092. Min Range: -10.2092

Max Act: 9.0325. Min Act: -0.0000

Data Index: 289518 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 10.2092. Min Range: -10.2092

Max Act: 8.9963. Min Act: -0.0000

Data Index: 1590212 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 10.2092. Min Range: -10.2092

Max Act: 9.1639. Min Act: -0.0000

Data Index: 1177308 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 10.2092. Min Range: -10.2092

Max Act: 9.4952. Min Act: -0.0000

Data Index: 908049 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 10.2092. Min Range: -10.2092

Max Act: 9.1296. Min Act: -0.0000

Data Index: 611845 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 10.2092. Min Range: -10.2092

Max Act: 8.9487. Min Act: -0.0000

Data Index: 1476713 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 10.2092. Min Range: -10.2092

Max Act: 8.7467. Min Act: -0.0000

Data Index: 585491 (The Pile)

Max Activating Token Index: 299

Text #15

Max Range: 10.2092. Min Range: -10.2092

Max Act: 8.7647. Min Act: -0.0000

Data Index: 240253 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 10.2092. Min Range: -10.2092

Max Act: 8.9830. Min Act: -0.0000

Data Index: 1343772 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 10.2092. Min Range: -10.2092

Max Act: 8.7485. Min Act: -0.0000

Data Index: 1184601 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 10.2092. Min Range: -10.2092

Max Act: 8.6141. Min Act: -0.0000

Data Index: 496588 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 10.2092. Min Range: -10.2092

Max Act: 8.7990. Min Act: -0.0000

Data Index: 1207555 (The Pile)

Max Activating Token Index: 644