Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1354 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2742. Min Act: -0.0000

Data Index: 78145 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2725. Min Act: -0.0001

Data Index: 977521 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2686. Min Act: -0.0001

Data Index: 1069706 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2553. Min Act: -0.0000

Data Index: 702831 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2444. Min Act: -0.0000

Data Index: 633050 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2419. Min Act: -0.0001

Data Index: 12715 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2289. Min Act: -0.0000

Data Index: 267854 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2303. Min Act: -0.0000

Data Index: 518073 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2263. Min Act: -0.0000

Data Index: 642108 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2294. Min Act: -0.0001

Data Index: 290999 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2256. Min Act: -0.0000

Data Index: 768886 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2240. Min Act: -0.0000

Data Index: 742176 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2217. Min Act: -0.0000

Data Index: 161711 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1152587 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2077. Min Act: -0.0001

Data Index: 332916 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1301078 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2106. Min Act: -0.0000

Data Index: 186276 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2171. Min Act: -0.0000

Data Index: 693732 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2002. Min Act: -0.0000

Data Index: 347888 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.1991. Min Act: -0.0000

Data Index: 882323 (C4 (Web Text))

Max Activating Token Index: 731