Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4098 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1463429 (Python Code)

Max Activating Token Index: 302

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0632. Min Act: -0.0000

Data Index: 946481 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1591213 (Python Code)

Max Activating Token Index: 612

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0600. Min Act: -0.0000

Data Index: 992417 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0516. Min Act: -0.0000

Data Index: 1447000 (Python Code)

Max Activating Token Index: 367

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1646966 (Python Code)

Max Activating Token Index: 731

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0586. Min Act: -0.0000

Data Index: 449458 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1264055 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0528. Min Act: -0.0000

Data Index: 244084 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1136241 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1082194 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1279012 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1590424 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0492. Min Act: -0.0000

Data Index: 1507382 (Python Code)

Max Activating Token Index: 527

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0509. Min Act: -0.0000

Data Index: 360075 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1571895 (Python Code)

Max Activating Token Index: 903

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1459504 (Python Code)

Max Activating Token Index: 819

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1655537 (Python Code)

Max Activating Token Index: 914

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0528. Min Act: -0.0000

Data Index: 910959 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0520. Min Act: -0.0000

Data Index: 130446 (C4 (Web Text))

Max Activating Token Index: 709