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

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

Neuron 2594 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.4232. Min Act: -0.0000

Data Index: 882127 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.4515. Min Act: -0.0000

Data Index: 347857 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.3435. Min Act: -0.0000

Data Index: 385959 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.4012. Min Act: -0.0000

Data Index: 856896 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.3339. Min Act: -0.0000

Data Index: 376162 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.2837. Min Act: -0.0000

Data Index: 805208 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.3111. Min Act: -0.0000

Data Index: 474223 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.3152. Min Act: -0.0000

Data Index: 601925 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.2160. Min Act: -0.0000

Data Index: 245906 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1268016 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.3622. Min Act: -0.0000

Data Index: 62697 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.3325. Min Act: -0.0000

Data Index: 61777 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.2652. Min Act: -0.0000

Data Index: 792437 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.2407. Min Act: -0.0000

Data Index: 676057 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.2013. Min Act: -0.0000

Data Index: 820102 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.2252. Min Act: -0.0000

Data Index: 766411 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.1820. Min Act: -0.0000

Data Index: 126093 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.1425. Min Act: -0.0000

Data Index: 390700 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.1812. Min Act: -0.0000

Data Index: 663916 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.1669. Min Act: -0.0000

Data Index: 573650 (C4 (Web Text))

Max Activating Token Index: 519