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

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

Neuron 638 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1044926 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1035535 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0590. Min Act: -0.0002

Data Index: 184738 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0556. Min Act: -0.0002

Data Index: 530045 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1283094 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0519. Min Act: -0.0002

Data Index: 102897 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0537. Min Act: -0.0001

Data Index: 272097 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0536. Min Act: -0.0002

Data Index: 94055 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0524. Min Act: -0.0001

Data Index: 257179 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0523. Min Act: -0.0002

Data Index: 817247 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0514. Min Act: -0.0002

Data Index: 951078 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1068343 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1177462 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0514. Min Act: -0.0002

Data Index: 475637 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0528. Min Act: -0.0002

Data Index: 309335 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1349999 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1063869 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0517. Min Act: -0.0002

Data Index: 703897 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0484. Min Act: -0.0002

Data Index: 189179 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0467. Min Act: -0.0002

Data Index: 921316 (C4 (Web Text))

Max Activating Token Index: 139