Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2453 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1750. Min Act: -0.0001

Data Index: 1046144 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1157745 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1771. Min Act: -0.0001

Data Index: 697593 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1646. Min Act: -0.0001

Data Index: 736962 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1179070 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1681. Min Act: -0.0001

Data Index: 728556 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1210410 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1637. Min Act: -0.0001

Data Index: 51382 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1677. Min Act: -0.0001

Data Index: 39616 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1606. Min Act: -0.0001

Data Index: 734888 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1607. Min Act: -0.0001

Data Index: 850180 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1538. Min Act: -0.0001

Data Index: 797460 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1314079 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1532. Min Act: -0.0001

Data Index: 267744 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1519. Min Act: -0.0001

Data Index: 152340 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1570. Min Act: -0.0001

Data Index: 359366 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1625. Min Act: -0.0001

Data Index: 415287 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1595. Min Act: -0.0001

Data Index: 416981 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1541. Min Act: -0.0001

Data Index: 669668 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1532. Min Act: -0.0001

Data Index: 289689 (C4 (Web Text))

Max Activating Token Index: 130