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

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

Neuron 5342 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1266709 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8860. Min Act: -0.0000

Data Index: 640083 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1185251 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7374. Min Act: -0.0000

Data Index: 557825 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1184475 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1071535 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6577. Min Act: -0.0000

Data Index: 848488 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1330122 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6512. Min Act: -0.0000

Data Index: 410800 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6477. Min Act: -0.0000

Data Index: 393510 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6232. Min Act: -0.0000

Data Index: 235385 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6552. Min Act: -0.0000

Data Index: 418148 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6468. Min Act: -0.0000

Data Index: 214107 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6224. Min Act: -0.0000

Data Index: 546477 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5965. Min Act: -0.0000

Data Index: 620047 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1078897 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6187. Min Act: -0.0000

Data Index: 432497 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5770. Min Act: -0.0000

Data Index: 142227 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5865. Min Act: -0.0000

Data Index: 501106 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5690. Min Act: -0.0000

Data Index: 235589 (C4 (Web Text))

Max Activating Token Index: 492