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

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

Neuron 4346 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7627. Min Act: -0.0000

Data Index: 935801 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7291. Min Act: -0.0000

Data Index: 115733 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6500. Min Act: -0.0000

Data Index: 658628 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.5392. Min Act: -0.0000

Data Index: 879671 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.4871. Min Act: -0.0000

Data Index: 218100 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.5625. Min Act: -0.0000

Data Index: 422774 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.4172. Min Act: -0.0000

Data Index: 699977 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.4563. Min Act: -0.0000

Data Index: 16517 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1007761 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.4304. Min Act: -0.0000

Data Index: 256646 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.4473. Min Act: -0.0000

Data Index: 739533 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.4547. Min Act: -0.0000

Data Index: 374218 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.3262. Min Act: -0.0000

Data Index: 73819 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.2565. Min Act: -0.0000

Data Index: 1206975 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.3178. Min Act: -0.0000

Data Index: 1115212 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.3137. Min Act: -0.0000

Data Index: 925150 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.1656. Min Act: -0.0000

Data Index: 521250 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.2753. Min Act: -0.0000

Data Index: 538738 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.3088. Min Act: -0.0000

Data Index: 406776 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.3106. Min Act: -0.0000

Data Index: 854244 (C4 (Web Text))

Max Activating Token Index: 347