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

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

Neuron 1016 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4774. Min Range: -3.4774

Max Act: 3.4774. Min Act: -0.0001

Data Index: 1397901 (Python Code)

Max Activating Token Index: 384

Text #1

Max Range: 3.4774. Min Range: -3.4774

Max Act: 3.4158. Min Act: -0.0001

Data Index: 254217 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.4774. Min Range: -3.4774

Max Act: 3.0173. Min Act: -0.0000

Data Index: 295443 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.9408. Min Act: -0.0000

Data Index: 95774 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.9767. Min Act: -0.0001

Data Index: 225097 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.7002. Min Act: -0.0001

Data Index: 1521655 (Python Code)

Max Activating Token Index: 431

Text #6

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.6480. Min Act: -0.0000

Data Index: 845002 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.6620. Min Act: -0.0001

Data Index: 280743 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.5904. Min Act: -0.0001

Data Index: 612447 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.4057. Min Act: -0.0001

Data Index: 1129419 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.4470. Min Act: -0.0001

Data Index: 1548693 (Python Code)

Max Activating Token Index: 600

Text #11

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.5962. Min Act: -0.0001

Data Index: 1373593 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.4214. Min Act: -0.0001

Data Index: 1003984 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.1352. Min Act: -0.0000

Data Index: 495667 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.2551. Min Act: -0.0001

Data Index: 1240285 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.3388. Min Act: -0.0000

Data Index: 1347452 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.4278. Min Act: -0.0000

Data Index: 517475 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.1336. Min Act: -0.0001

Data Index: 696693 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.3780. Min Act: -0.0001

Data Index: 875473 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 3.4774. Min Range: -3.4774

Max Act: 2.2201. Min Act: -0.0001

Data Index: 1095316 (C4 (Web Text))

Max Activating Token Index: 20