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

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

Neuron 3665 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.4031. Min Act: -0.0000

Data Index: 1357906 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1589. Min Act: -0.0000

Data Index: 378584 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1226668 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.9099. Min Act: -0.0000

Data Index: 968298 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8489. Min Act: -0.0000

Data Index: 918046 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8952. Min Act: -0.0000

Data Index: 798386 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8956. Min Act: -0.0000

Data Index: 670677 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1078630 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8309. Min Act: -0.0001

Data Index: 470840 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8589. Min Act: -0.0001

Data Index: 677055 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1201398 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1141821 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.7949. Min Act: -0.0000

Data Index: 75947 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1207801 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1110371 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.7675. Min Act: -0.0000

Data Index: 688366 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.7846. Min Act: -0.0000

Data Index: 424898 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.7582. Min Act: -0.0000

Data Index: 498786 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1007951 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.6903. Min Act: -0.0000

Data Index: 798999 (C4 (Web Text))

Max Activating Token Index: 919