Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 845 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.9209. Min Act: -0.0001

Data Index: 461057 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.9384. Min Act: -0.0001

Data Index: 142544 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8807. Min Act: -0.0001

Data Index: 1309708 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8587. Min Act: -0.0001

Data Index: 552362 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8306. Min Act: -0.0001

Data Index: 1303409 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8225. Min Act: -0.0001

Data Index: 717277 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8461. Min Act: -0.0001

Data Index: 796330 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8637. Min Act: -0.0001

Data Index: 724775 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8027. Min Act: -0.0001

Data Index: 267180 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8662. Min Act: -0.0001

Data Index: 1042795 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8064. Min Act: -0.0001

Data Index: 1715 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7809. Min Act: -0.0001

Data Index: 773598 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7788. Min Act: -0.0001

Data Index: 909380 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6788. Min Act: -0.0001

Data Index: 936336 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7549. Min Act: -0.0001

Data Index: 1354457 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7516. Min Act: -0.0001

Data Index: 193671 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7765. Min Act: -0.0001

Data Index: 384366 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7340. Min Act: -0.0001

Data Index: 875218 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7290. Min Act: -0.0001

Data Index: 1126870 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7231. Min Act: -0.0001

Data Index: 721755 (C4 (Web Text))

Max Activating Token Index: 564