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

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

Neuron 6010 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4749. Min Range: -4.4749

Max Act: 4.4749. Min Act: -0.0000

Data Index: 759884 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 4.4749. Min Range: -4.4749

Max Act: 4.1901. Min Act: -0.0000

Data Index: 829452 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.8082. Min Act: -0.0000

Data Index: 1070821 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.7670. Min Act: -0.0000

Data Index: 265093 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.7147. Min Act: -0.0000

Data Index: 476488 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.6440. Min Act: 0.0000

Data Index: 746783 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.6466. Min Act: -0.0000

Data Index: 913462 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.2351. Min Act: -0.0000

Data Index: 259548 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.0957. Min Act: -0.0000

Data Index: 280692 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.0796. Min Act: -0.0000

Data Index: 275194 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.2627. Min Act: -0.0000

Data Index: 274266 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.1500. Min Act: -0.0000

Data Index: 1344719 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.0591. Min Act: -0.0000

Data Index: 1201861 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.1845. Min Act: -0.0000

Data Index: 309051 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 4.4749. Min Range: -4.4749

Max Act: 2.8809. Min Act: -0.0000

Data Index: 643174 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 4.4749. Min Range: -4.4749

Max Act: 2.8902. Min Act: -0.0000

Data Index: 1230848 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.0147. Min Act: -0.0000

Data Index: 1111010 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 4.4749. Min Range: -4.4749

Max Act: 3.1409. Min Act: -0.0000

Data Index: 574737 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 4.4749. Min Range: -4.4749

Max Act: 2.9747. Min Act: -0.0000

Data Index: 1175819 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 4.4749. Min Range: -4.4749

Max Act: 2.8161. Min Act: -0.0000

Data Index: 551071 (C4 (Web Text))

Max Activating Token Index: 97