Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4347 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0622. Min Range: -2.0622

Max Act: 2.0622. Min Act: -0.0000

Data Index: 230729 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 2.0622. Min Range: -2.0622

Max Act: 2.0100. Min Act: -0.0000

Data Index: 198585 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.9626. Min Act: -0.0000

Data Index: 1098602 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.9224. Min Act: -0.0000

Data Index: 1162227 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.8061. Min Act: -0.0001

Data Index: 167993 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.8482. Min Act: -0.0000

Data Index: 427003 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.8232. Min Act: -0.0000

Data Index: 227244 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.7080. Min Act: -0.0000

Data Index: 305755 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.6941. Min Act: -0.0000

Data Index: 324153 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.6005. Min Act: -0.0000

Data Index: 778349 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.7236. Min Act: -0.0000

Data Index: 27642 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.6371. Min Act: -0.0001

Data Index: 538634 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.6269. Min Act: -0.0000

Data Index: 1192034 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.5743. Min Act: -0.0001

Data Index: 683871 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.5576. Min Act: -0.0000

Data Index: 1175202 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1016704 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.4538. Min Act: -0.0000

Data Index: 965340 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.5248. Min Act: -0.0001

Data Index: 507168 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.4854. Min Act: -0.0000

Data Index: 535891 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 2.0622. Min Range: -2.0622

Max Act: 1.4849. Min Act: -0.0000

Data Index: 782913 (C4 (Web Text))

Max Activating Token Index: 189