Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2691 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.8497. Min Act: -0.0001

Data Index: 1339619 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7332. Min Act: -0.0001

Data Index: 561911 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7173. Min Act: -0.0002

Data Index: 783800 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7329. Min Act: -0.0002

Data Index: 140100 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7266. Min Act: -0.0001

Data Index: 1302639 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6593. Min Act: -0.0002

Data Index: 346270 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6858. Min Act: -0.0002

Data Index: 442232 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6607. Min Act: -0.0001

Data Index: 119183 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6742. Min Act: -0.0001

Data Index: 313340 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6951. Min Act: -0.0002

Data Index: 152826 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6477. Min Act: -0.0001

Data Index: 501793 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6609. Min Act: -0.0001

Data Index: 558911 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6488. Min Act: -0.0001

Data Index: 482716 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6628. Min Act: -0.0002

Data Index: 857756 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6204. Min Act: -0.0001

Data Index: 1222384 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6390. Min Act: -0.0001

Data Index: 1246795 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6822. Min Act: -0.0001

Data Index: 604777 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6476. Min Act: -0.0002

Data Index: 1357163 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6435. Min Act: -0.0001

Data Index: 206814 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6498. Min Act: -0.0001

Data Index: 1052855 (C4 (Web Text))

Max Activating Token Index: 249