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

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

Neuron 2821 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0650. Min Act: -0.0000

Data Index: 717317 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: -0.0000

Data Index: 731759 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0649. Min Act: -0.0000

Data Index: 964190 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0632. Min Act: -0.0000

Data Index: 270634 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1150583 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0585. Min Act: -0.0000

Data Index: 286081 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1583037 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0574. Min Act: -0.0000

Data Index: 433925 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1523122 (Python Code)

Max Activating Token Index: 919

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1014232 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0586. Min Act: -0.0000

Data Index: 572972 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0511. Min Act: -0.0000

Data Index: 1520605 (Python Code)

Max Activating Token Index: 1008

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0540. Min Act: -0.0000

Data Index: 66062 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1227245 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0589. Min Act: -0.0000

Data Index: 1019590 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0561. Min Act: -0.0000

Data Index: 506091 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0453. Min Act: -0.0000

Data Index: 122802 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1400813 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0434. Min Act: -0.0000

Data Index: 1639193 (Python Code)

Max Activating Token Index: 939

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0543. Min Act: -0.0000

Data Index: 679350 (C4 (Web Text))

Max Activating Token Index: 903