Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 581 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0726. Min Act: -0.0003

Data Index: 266313 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0658. Min Act: -0.0004

Data Index: 770003 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0634. Min Act: -0.0004

Data Index: 648836 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0631. Min Act: -0.0004

Data Index: 245922 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0646. Min Act: -0.0003

Data Index: 421597 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0593. Min Act: -0.0004

Data Index: 1153997 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0585. Min Act: -0.0003

Data Index: 186782 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0621. Min Act: -0.0004

Data Index: 789733 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0593. Min Act: -0.0004

Data Index: 368826 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0604. Min Act: -0.0004

Data Index: 1164945 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0577. Min Act: -0.0003

Data Index: 1066390 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0583. Min Act: -0.0004

Data Index: 720770 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0597. Min Act: -0.0004

Data Index: 1025527 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0574. Min Act: -0.0004

Data Index: 151504 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0570. Min Act: -0.0003

Data Index: 204591 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0590. Min Act: -0.0004

Data Index: 1244555 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0576. Min Act: -0.0003

Data Index: 62593 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1424781 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1064882 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0569. Min Act: -0.0004

Data Index: 1272207 (C4 (Web Text))

Max Activating Token Index: 18