Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 646 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1187519 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0591. Min Act: -0.0002

Data Index: 996179 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1218283 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0592. Min Act: -0.0002

Data Index: 640011 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0579. Min Act: -0.0002

Data Index: 165978 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0574. Min Act: -0.0002

Data Index: 921333 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0558. Min Act: -0.0002

Data Index: 250431 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0540. Min Act: -0.0002

Data Index: 38670 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0560. Min Act: -0.0002

Data Index: 936976 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0553. Min Act: -0.0002

Data Index: 778855 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0535. Min Act: -0.0002

Data Index: 196167 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0524. Min Act: -0.0002

Data Index: 383056 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0529. Min Act: -0.0002

Data Index: 952971 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1284779 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0540. Min Act: -0.0002

Data Index: 386506 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0531. Min Act: -0.0002

Data Index: 711448 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1317234 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0516. Min Act: -0.0002

Data Index: 118913 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0521. Min Act: -0.0002

Data Index: 500612 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0519. Min Act: -0.0002

Data Index: 588061 (C4 (Web Text))

Max Activating Token Index: 860