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

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

Neuron 338 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.5537. Min Act: -0.0000

Data Index: 178809 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.5234. Min Act: -0.0000

Data Index: 266717 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1124152 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.5008. Min Act: -0.0000

Data Index: 769052 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.5047. Min Act: -0.0000

Data Index: 515275 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.5012. Min Act: -0.0000

Data Index: 913845 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4971. Min Act: -0.0000

Data Index: 432313 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1104132 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4902. Min Act: -0.0000

Data Index: 31812 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.5042. Min Act: -0.0000

Data Index: 298393 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.5009. Min Act: -0.0000

Data Index: 385027 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.5103. Min Act: -0.0000

Data Index: 128096 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4938. Min Act: -0.0000

Data Index: 578776 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4496. Min Act: -0.0000

Data Index: 715489 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1113553 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4343. Min Act: -0.0000

Data Index: 44960 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4595. Min Act: -0.0000

Data Index: 47163 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4161. Min Act: -0.0000

Data Index: 785863 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4574. Min Act: -0.0000

Data Index: 859485 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4334. Min Act: -0.0000

Data Index: 379920 (C4 (Web Text))

Max Activating Token Index: 931