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

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

Neuron 1775 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1043895 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1521. Min Act: -0.0001

Data Index: 145973 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1517. Min Act: -0.0001

Data Index: 322449 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1581. Min Act: -0.0001

Data Index: 1289356 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1575. Min Act: -0.0001

Data Index: 317572 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1568. Min Act: -0.0001

Data Index: 521598 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1334. Min Act: -0.0001

Data Index: 385618 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1170444 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1148382 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1055047 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1229787 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1051289 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1541. Min Act: -0.0001

Data Index: 88430 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1049817 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1171907 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1475. Min Act: -0.0001

Data Index: 811870 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1471. Min Act: -0.0001

Data Index: 354466 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1363. Min Act: -0.0001

Data Index: 973995 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1375. Min Act: -0.0001

Data Index: 362366 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1443. Min Act: -0.0001

Data Index: 350339 (C4 (Web Text))

Max Activating Token Index: 892