Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3431 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0620. Min Range: -1.0620

Max Act: 1.0620. Min Act: -0.0000

Data Index: 345287 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 1.0620. Min Range: -1.0620

Max Act: 1.0001. Min Act: -0.0001

Data Index: 258447 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.9950. Min Act: -0.0001

Data Index: 799983 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.9041. Min Act: -0.0000

Data Index: 637574 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.9304. Min Act: -0.0001

Data Index: 1277017 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1308950 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8827. Min Act: -0.0001

Data Index: 326529 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1071107 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8925. Min Act: -0.0000

Data Index: 938370 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8212. Min Act: -0.0001

Data Index: 588631 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1116005 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8363. Min Act: -0.0000

Data Index: 802778 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8523. Min Act: -0.0000

Data Index: 107554 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1247854 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.7961. Min Act: -0.0000

Data Index: 189775 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8150. Min Act: 0.0001

Data Index: 278272 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8018. Min Act: -0.0001

Data Index: 521203 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1233632 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1049598 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.0620. Min Range: -1.0620

Max Act: 0.7809. Min Act: -0.0000

Data Index: 705954 (C4 (Web Text))

Max Activating Token Index: 110