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

Dataset: The Pile

Neuron 4351 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1423344 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1842565 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1767. Min Act: -0.0000

Data Index: 760278 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1439650 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1457. Min Act: -0.0000

Data Index: 952397 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1084695 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1546. Min Act: -0.0000

Data Index: 437172 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1940865 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1270001 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1572. Min Act: -0.0000

Data Index: 230014 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1433. Min Act: -0.0000

Data Index: 5465 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1424. Min Act: -0.0000

Data Index: 998012 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1259022 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1144488 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1969678 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1294. Min Act: -0.0000

Data Index: 787978 (The Pile)

Max Activating Token Index: 164

Text #16

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1456730 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1335. Min Act: -0.0000

Data Index: 686326 (The Pile)

Max Activating Token Index: 316

Text #18

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1533763 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1777994 (The Pile)

Max Activating Token Index: 165