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

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

Neuron 1423 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.8100. Min Act: -0.0000

Data Index: 867608 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.8678. Min Act: -0.0000

Data Index: 946215 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1075550 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7126. Min Act: -0.0000

Data Index: 315389 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7678. Min Act: -0.0000

Data Index: 652881 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7934. Min Act: -0.0000

Data Index: 175445 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7861. Min Act: -0.0000

Data Index: 623720 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7882. Min Act: -0.0000

Data Index: 582638 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7023. Min Act: -0.0000

Data Index: 836097 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7408. Min Act: -0.0000

Data Index: 370141 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7617. Min Act: -0.0000

Data Index: 367437 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1308238 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1321299 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7717. Min Act: -0.0000

Data Index: 581162 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7100. Min Act: -0.0000

Data Index: 550026 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.8318. Min Act: -0.0000

Data Index: 797262 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1261140 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1068797 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.7085. Min Act: -0.0000

Data Index: 701180 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.8678. Min Range: -0.8678

Max Act: 0.6812. Min Act: -0.0000

Data Index: 718626 (C4 (Web Text))

Max Activating Token Index: 604