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

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

Neuron 5164 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.8832. Min Act: -0.0000

Data Index: 651680 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.6931. Min Act: -0.0000

Data Index: 54340 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5548. Min Act: -0.0000

Data Index: 73105 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.4207. Min Act: -0.0000

Data Index: 1122142 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.4505. Min Act: -0.0000

Data Index: 738319 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.4705. Min Act: -0.0000

Data Index: 434563 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.3324. Min Act: -0.0000

Data Index: 811767 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.2989. Min Act: -0.0000

Data Index: 1056231 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1033021 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.1582. Min Act: -0.0000

Data Index: 1266885 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.1321. Min Act: -0.0000

Data Index: 172043 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.1707. Min Act: -0.0001

Data Index: 612193 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.1175. Min Act: -0.0000

Data Index: 171989 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.1136. Min Act: -0.0000

Data Index: 378792 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.1053. Min Act: -0.0001

Data Index: 742975 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.1446. Min Act: -0.0000

Data Index: 352532 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.0818. Min Act: -0.0000

Data Index: 1088808 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.1417. Min Act: -0.0000

Data Index: 489107 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.0684. Min Act: -0.0000

Data Index: 714329 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.0710. Min Act: -0.0000

Data Index: 176556 (C4 (Web Text))

Max Activating Token Index: 175