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

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

Neuron 4339 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2986. Min Act: -0.0000

Data Index: 480984 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2512. Min Act: -0.0000

Data Index: 309220 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1219561 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1999. Min Act: -0.0000

Data Index: 371813 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1031691 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1147911 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1420470 (Python Code)

Max Activating Token Index: 413

Text #7

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1182439 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1650. Min Act: -0.0000

Data Index: 750200 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1538. Min Act: -0.0000

Data Index: 815576 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1518250 (Python Code)

Max Activating Token Index: 476

Text #11

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1035783 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1549. Min Act: -0.0000

Data Index: 673272 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1243132 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1527. Min Act: -0.0000

Data Index: 394357 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1574. Min Act: -0.0000

Data Index: 894588 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1497. Min Act: -0.0000

Data Index: 304429 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1241016 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1526. Min Act: -0.0000

Data Index: 986669 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.1539. Min Act: -0.0000

Data Index: 222111 (C4 (Web Text))

Max Activating Token Index: 118