Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 223 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0576. Min Act: -0.0006

Data Index: 1469349 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0593. Min Act: -0.0006

Data Index: 1214727 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0590. Min Act: -0.0006

Data Index: 1397314 (Python Code)

Max Activating Token Index: 583

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0586. Min Act: -0.0006

Data Index: 1654559 (Python Code)

Max Activating Token Index: 236

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0596. Min Act: -0.0006

Data Index: 635290 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0005

Data Index: 1484398 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0541. Min Act: -0.0006

Data Index: 1391269 (Python Code)

Max Activating Token Index: 983

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0603. Min Act: -0.0005

Data Index: 314712 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0542. Min Act: -0.0005

Data Index: 797793 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0583. Min Act: -0.0006

Data Index: 1611871 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0556. Min Act: -0.0005

Data Index: 177575 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0576. Min Act: -0.0006

Data Index: 1361954 (Python Code)

Max Activating Token Index: 231

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0572. Min Act: -0.0005

Data Index: 277133 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0521. Min Act: -0.0005

Data Index: 1225982 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0552. Min Act: -0.0006

Data Index: 1440020 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0537. Min Act: -0.0005

Data Index: 952387 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0560. Min Act: -0.0006

Data Index: 1211478 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0557. Min Act: -0.0006

Data Index: 1478685 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0523. Min Act: -0.0006

Data Index: 1151697 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0542. Min Act: -0.0006

Data Index: 1583086 (Python Code)

Max Activating Token Index: 933