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

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

Neuron 1031 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.7997. Min Act: -0.0000

Data Index: 368226 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.7813. Min Act: -0.0001

Data Index: 800314 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.7062. Min Act: -0.0000

Data Index: 269454 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6820. Min Act: -0.0000

Data Index: 696293 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6731. Min Act: -0.0000

Data Index: 259616 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6685. Min Act: -0.0001

Data Index: 1252653 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1318252 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5764. Min Act: -0.0000

Data Index: 975160 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1184033 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6314. Min Act: -0.0001

Data Index: 589700 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6087. Min Act: -0.0001

Data Index: 526525 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5805. Min Act: -0.0000

Data Index: 54087 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1446367 (Python Code)

Max Activating Token Index: 881

Text #13

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5891. Min Act: -0.0000

Data Index: 370996 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1411190 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5473. Min Act: -0.0000

Data Index: 958275 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5483. Min Act: -0.0001

Data Index: 285660 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6121. Min Act: -0.0000

Data Index: 60268 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5537. Min Act: -0.0000

Data Index: 913415 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1295610 (C4 (Web Text))

Max Activating Token Index: 9