Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 792 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0619. Min Act: -0.0003

Data Index: 963565 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0639. Min Act: -0.0003

Data Index: 829364 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1065314 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0548. Min Act: -0.0003

Data Index: 260155 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0515. Min Act: -0.0003

Data Index: 49374 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0575. Min Act: -0.0003

Data Index: 737001 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0538. Min Act: -0.0003

Data Index: 215472 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0572. Min Act: -0.0003

Data Index: 467089 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0569. Min Act: -0.0003

Data Index: 273755 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1007651 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0555. Min Act: -0.0003

Data Index: 204406 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0527. Min Act: -0.0003

Data Index: 702691 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1397438 (Python Code)

Max Activating Token Index: 610

Text #13

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1007464 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0516. Min Act: -0.0004

Data Index: 742330 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0513. Min Act: -0.0003

Data Index: 280990 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0512. Min Act: -0.0003

Data Index: 841503 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0503. Min Act: -0.0004

Data Index: 453983 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0538. Min Act: -0.0004

Data Index: 911876 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0498. Min Act: -0.0003

Data Index: 358205 (C4 (Web Text))

Max Activating Token Index: 9