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

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

Neuron 586 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: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0003

Data Index: 551273 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0703. Min Act: -0.0003

Data Index: 1152385 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1581566 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1648126 (Python Code)

Max Activating Token Index: 335

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1451817 (Python Code)

Max Activating Token Index: 918

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1296147 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0568. Min Act: -0.0003

Data Index: 946089 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0576. Min Act: -0.0003

Data Index: 626631 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0582. Min Act: -0.0003

Data Index: 462810 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0563. Min Act: -0.0004

Data Index: 1077260 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0569. Min Act: -0.0003

Data Index: 469253 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1562177 (Python Code)

Max Activating Token Index: 533

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0580. Min Act: -0.0003

Data Index: 587631 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1156974 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0555. Min Act: -0.0003

Data Index: 78146 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1132506 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0540. Min Act: -0.0003

Data Index: 427722 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1454799 (Python Code)

Max Activating Token Index: 940

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0558. Min Act: -0.0003

Data Index: 790381 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1190487 (C4 (Web Text))

Max Activating Token Index: 864