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

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

Neuron 2848 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3625. Min Act: -0.0000

Data Index: 861319 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3561. Min Act: -0.0000

Data Index: 561847 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3356. Min Act: -0.0000

Data Index: 316805 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3218. Min Act: -0.0000

Data Index: 195321 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3357. Min Act: -0.0000

Data Index: 681037 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3205. Min Act: -0.0000

Data Index: 790585 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2819. Min Act: -0.0000

Data Index: 178787 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3006. Min Act: -0.0000

Data Index: 1205571 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1025604 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2210. Min Act: -0.0000

Data Index: 960244 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2652. Min Act: -0.0000

Data Index: 52470 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2457. Min Act: -0.0000

Data Index: 323044 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1189578 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2354. Min Act: -0.0000

Data Index: 150226 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2151. Min Act: -0.0000

Data Index: 919847 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2571. Min Act: -0.0000

Data Index: 587620 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2087. Min Act: -0.0000

Data Index: 995215 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2236. Min Act: -0.0000

Data Index: 953757 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2334. Min Act: -0.0000

Data Index: 28776 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2234. Min Act: -0.0000

Data Index: 573915 (C4 (Web Text))

Max Activating Token Index: 176