Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 627 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0005

Data Index: 905668 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0467. Min Act: -0.0005

Data Index: 241167 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0424. Min Act: -0.0005

Data Index: 287478 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0429. Min Act: -0.0005

Data Index: 262846 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0416. Min Act: -0.0005

Data Index: 400836 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0379. Min Act: -0.0005

Data Index: 1204632 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0377. Min Act: -0.0005

Data Index: 348600 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0354. Min Act: -0.0005

Data Index: 1106918 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0394. Min Act: -0.0005

Data Index: 826791 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0401. Min Act: -0.0005

Data Index: 528626 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0374. Min Act: -0.0005

Data Index: 1174472 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0380. Min Act: -0.0005

Data Index: 929704 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0370. Min Act: -0.0005

Data Index: 867761 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0377. Min Act: -0.0005

Data Index: 1205057 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0337. Min Act: -0.0005

Data Index: 874398 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0366. Min Act: -0.0005

Data Index: 676160 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0351. Min Act: -0.0005

Data Index: 257695 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0373. Min Act: -0.0005

Data Index: 606636 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0374. Min Act: -0.0005

Data Index: 518429 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0352. Min Act: -0.0005

Data Index: 1300783 (C4 (Web Text))

Max Activating Token Index: 500