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

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

Neuron 1268 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: 0.0565. Min Range: -0.0565

Max Act: 0.0565. Min Act: -0.0002

Data Index: 337943 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0537. Min Act: -0.0003

Data Index: 745451 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0519. Min Act: -0.0003

Data Index: 194721 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1269682 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0501. Min Act: -0.0003

Data Index: 569203 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1345133 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0474. Min Act: -0.0003

Data Index: 336241 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1302130 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1090501 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0448. Min Act: -0.0004

Data Index: 698567 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0465. Min Act: -0.0003

Data Index: 153821 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0466. Min Act: -0.0003

Data Index: 172285 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0461. Min Act: -0.0003

Data Index: 293414 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0467. Min Act: -0.0004

Data Index: 1303253 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0455. Min Act: -0.0002

Data Index: 761915 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0448. Min Act: -0.0004

Data Index: 928164 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0444. Min Act: -0.0003

Data Index: 188395 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0445. Min Act: -0.0004

Data Index: 554546 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0459. Min Act: -0.0003

Data Index: 774843 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0448. Min Act: -0.0002

Data Index: 130931 (C4 (Web Text))

Max Activating Token Index: 521