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

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

Neuron 3888 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1204864 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0679. Min Act: -0.0002

Data Index: 899241 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0550. Min Act: -0.0002

Data Index: 852517 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0674. Min Act: -0.0002

Data Index: 568365 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0532. Min Act: -0.0002

Data Index: 381751 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0549. Min Act: -0.0002

Data Index: 414524 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1524359 (Python Code)

Max Activating Token Index: 1020

Text #7

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1191747 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0627. Min Act: -0.0002

Data Index: 330321 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0583. Min Act: -0.0002

Data Index: 88664 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0533. Min Act: -0.0002

Data Index: 352325 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0494. Min Act: -0.0002

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0653. Min Act: -0.0002

Data Index: 13884 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1579629 (Python Code)

Max Activating Token Index: 832

Text #14

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1642194 (Python Code)

Max Activating Token Index: 1009

Text #15

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1431627 (Python Code)

Max Activating Token Index: 954

Text #16

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1185536 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0516. Min Act: -0.0002

Data Index: 987217 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1630316 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1307613 (C4 (Web Text))

Max Activating Token Index: 961