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

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

Neuron 320 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1021844 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0694. Min Act: -0.0002

Data Index: 776558 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0694. Min Act: -0.0002

Data Index: 99309 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0708. Min Act: -0.0002

Data Index: 986646 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0675. Min Act: -0.0003

Data Index: 359509 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0666. Min Act: -0.0002

Data Index: 278386 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0651. Min Act: -0.0002

Data Index: 300461 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0623. Min Act: -0.0002

Data Index: 137134 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1249240 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0628. Min Act: -0.0002

Data Index: 672318 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0594. Min Act: -0.0002

Data Index: 339228 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0599. Min Act: -0.0002

Data Index: 193851 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0612. Min Act: -0.0002

Data Index: 510930 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0600. Min Act: -0.0002

Data Index: 904528 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0599. Min Act: -0.0002

Data Index: 205458 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0586. Min Act: -0.0002

Data Index: 159504 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1647089 (Python Code)

Max Activating Token Index: 674

Text #17

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1106618 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1227654 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0558. Min Act: -0.0002

Data Index: 555308 (C4 (Web Text))

Max Activating Token Index: 588