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

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

Neuron 4353 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1310929 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0600. Min Act: -0.0003

Data Index: 669086 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1060561 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0547. Min Act: -0.0003

Data Index: 622415 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0517. Min Act: -0.0003

Data Index: 685182 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1065421 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0529. Min Act: -0.0002

Data Index: 634599 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1133024 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0492. Min Act: -0.0003

Data Index: 436756 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0481. Min Act: -0.0002

Data Index: 804628 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1017110 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0478. Min Act: -0.0003

Data Index: 603041 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0481. Min Act: -0.0003

Data Index: 811228 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0490. Min Act: -0.0002

Data Index: 259814 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1133269 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1241245 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0465. Min Act: -0.0003

Data Index: 681017 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0437. Min Act: -0.0003

Data Index: 282525 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0465. Min Act: -0.0003

Data Index: 337854 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0444. Min Act: -0.0003

Data Index: 325671 (C4 (Web Text))

Max Activating Token Index: 985