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

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

Neuron 2918 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0739. Min Act: -0.0000

Data Index: 1048884 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1037317 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0653. Min Act: -0.0000

Data Index: 914635 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0600. Min Act: -0.0001

Data Index: 443344 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0625. Min Act: -0.0001

Data Index: 223161 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0599. Min Act: -0.0000

Data Index: 55603 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0578. Min Act: -0.0000

Data Index: 218986 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0567. Min Act: -0.0001

Data Index: 22181 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1279369 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1167122 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1253140 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0513. Min Act: -0.0001

Data Index: 775572 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1340893 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0480. Min Act: -0.0000

Data Index: 523542 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1127621 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1260839 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0564. Min Act: -0.0001

Data Index: 415609 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0468. Min Act: -0.0001

Data Index: 578887 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1130008 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0492. Min Act: -0.0000

Data Index: 187476 (C4 (Web Text))

Max Activating Token Index: 624