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

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

Neuron 2929 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.8511. Min Act: -0.0001

Data Index: 448964 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.9532. Min Act: -0.0001

Data Index: 307394 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.9051. Min Act: -0.0001

Data Index: 1144083 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.8846. Min Act: -0.0001

Data Index: 1142574 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.7712. Min Act: -0.0001

Data Index: 629527 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.5616. Min Act: -0.0001

Data Index: 112473 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.6378. Min Act: -0.0001

Data Index: 886790 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.5533. Min Act: -0.0001

Data Index: 298555 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.6333. Min Act: -0.0001

Data Index: 650669 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.4374. Min Act: -0.0001

Data Index: 1245173 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.5963. Min Act: -0.0001

Data Index: 789945 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.6626. Min Act: -0.0001

Data Index: 5925 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.5843. Min Act: -0.0001

Data Index: 425448 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.5806. Min Act: -0.0001

Data Index: 1279659 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.5597. Min Act: -0.0001

Data Index: 645966 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.5313. Min Act: -0.0001

Data Index: 60498 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.4256. Min Act: -0.0001

Data Index: 1236479 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.4146. Min Act: -0.0001

Data Index: 981036 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.5057. Min Act: -0.0001

Data Index: 581240 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.4775. Min Act: -0.0001

Data Index: 830856 (C4 (Web Text))

Max Activating Token Index: 825