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

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

Neuron 1635 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: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0004

Data Index: 468346 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0582. Min Act: -0.0003

Data Index: 951460 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0559. Min Act: -0.0003

Data Index: 443315 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1326844 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0542. Min Act: -0.0003

Data Index: 390983 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0527. Min Act: -0.0003

Data Index: 512930 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1012244 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1291665 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0510. Min Act: -0.0003

Data Index: 327528 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0511. Min Act: -0.0003

Data Index: 439064 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0518. Min Act: -0.0003

Data Index: 510426 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0489. Min Act: -0.0003

Data Index: 608424 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0492. Min Act: -0.0003

Data Index: 209564 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0490. Min Act: -0.0004

Data Index: 415825 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0498. Min Act: -0.0004

Data Index: 401126 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0474. Min Act: -0.0003

Data Index: 607030 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0483. Min Act: -0.0003

Data Index: 362969 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0467. Min Act: -0.0003

Data Index: 865102 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1001632 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0483. Min Act: -0.0003

Data Index: 104157 (C4 (Web Text))

Max Activating Token Index: 239