Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1047 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.3044. Min Act: -0.0001

Data Index: 1323733 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.1652. Min Act: -0.0001

Data Index: 901136 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.1665. Min Act: -0.0001

Data Index: 848508 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0350. Min Act: -0.0001

Data Index: 122243 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0765. Min Act: -0.0001

Data Index: 1204960 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0619. Min Act: -0.0001

Data Index: 7409 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0464. Min Act: -0.0001

Data Index: 690802 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0033. Min Act: -0.0001

Data Index: 43343 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0379. Min Act: -0.0001

Data Index: 604791 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0125. Min Act: -0.0001

Data Index: 939116 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0147. Min Act: -0.0001

Data Index: 1323863 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9751. Min Act: -0.0001

Data Index: 1227726 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9525. Min Act: -0.0001

Data Index: 752934 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0345. Min Act: -0.0001

Data Index: 522118 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9282. Min Act: -0.0001

Data Index: 73886 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9235. Min Act: -0.0001

Data Index: 659906 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9806. Min Act: -0.0001

Data Index: 1082593 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.8560. Min Act: -0.0001

Data Index: 559456 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9440. Min Act: -0.0001

Data Index: 371621 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9361. Min Act: -0.0001

Data Index: 1250947 (C4 (Web Text))

Max Activating Token Index: 45