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

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

Neuron 276 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.1112. Min Act: -0.0000

Data Index: 495109 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1026545 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0308. Min Act: -0.0000

Data Index: 853592 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9685. Min Act: 0.0000

Data Index: 60790 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1202207 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9623. Min Act: -0.0000

Data Index: 271860 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8955. Min Act: -0.0000

Data Index: 500574 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9236. Min Act: 0.0000

Data Index: 340531 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9420. Min Act: 0.0000

Data Index: 1026120 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9388. Min Act: -0.0000

Data Index: 978228 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8649. Min Act: 0.0000

Data Index: 662488 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9324. Min Act: -0.0000

Data Index: 147838 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9019. Min Act: 0.0001

Data Index: 867516 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8511. Min Act: 0.0000

Data Index: 998618 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9045. Min Act: -0.0000

Data Index: 437941 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9033. Min Act: -0.0000

Data Index: 344134 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8940. Min Act: -0.0000

Data Index: 738765 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8513. Min Act: -0.0000

Data Index: 428331 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8125. Min Act: 0.0000

Data Index: 621351 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8294. Min Act: -0.0000

Data Index: 166553 (C4 (Web Text))

Max Activating Token Index: 573