Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4554 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0002

Data Index: 786528 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0648. Min Act: -0.0002

Data Index: 690529 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0638. Min Act: -0.0002

Data Index: 841624 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0642. Min Act: -0.0002

Data Index: 551016 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1427409 (Python Code)

Max Activating Token Index: 480

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1307229 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1151446 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0595. Min Act: -0.0002

Data Index: 215986 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0581. Min Act: -0.0002

Data Index: 835290 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1540769 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1533823 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1565349 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0546. Min Act: -0.0002

Data Index: 935493 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0554. Min Act: -0.0002

Data Index: 529933 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1410768 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0543. Min Act: -0.0002

Data Index: 375121 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0539. Min Act: -0.0002

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0528. Min Act: -0.0002

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1496040 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1195118 (C4 (Web Text))

Max Activating Token Index: 244