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

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

Neuron 4445 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0234. Min Range: -1.0234

Max Act: 1.0234. Min Act: -0.0000

Data Index: 698776 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 1.0234. Min Range: -1.0234

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1054730 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8754. Min Act: -0.0000

Data Index: 676665 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1190654 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8493. Min Act: -0.0000

Data Index: 833609 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1284630 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8507. Min Act: -0.0000

Data Index: 517683 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.9040. Min Act: -0.0000

Data Index: 633731 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8444. Min Act: -0.0000

Data Index: 403863 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8452. Min Act: -0.0000

Data Index: 525634 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8236. Min Act: -0.0000

Data Index: 796092 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1234707 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.7606. Min Act: -0.0000

Data Index: 1354189 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.7594. Min Act: -0.0000

Data Index: 839526 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.7821. Min Act: -0.0000

Data Index: 965544 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.7593. Min Act: -0.0000

Data Index: 579725 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1082749 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.7548. Min Act: -0.0000

Data Index: 868947 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.7722. Min Act: -0.0000

Data Index: 576968 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.7694. Min Act: -0.0000

Data Index: 550804 (C4 (Web Text))

Max Activating Token Index: 882