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

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

Neuron 2586 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.4658. Min Act: -0.0001

Data Index: 187920 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.5148. Min Act: -0.0001

Data Index: 1331599 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.4635. Min Act: -0.0001

Data Index: 531638 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.3097. Min Act: -0.0001

Data Index: 3509 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.3440. Min Act: -0.0001

Data Index: 89334 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.2917. Min Act: -0.0001

Data Index: 234230 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.2470. Min Act: -0.0001

Data Index: 1115167 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.2234. Min Act: -0.0001

Data Index: 886342 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.2716. Min Act: -0.0001

Data Index: 860288 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.2300. Min Act: -0.0001

Data Index: 270705 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.2100. Min Act: -0.0001

Data Index: 121983 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.1296. Min Act: -0.0001

Data Index: 681051 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.2147. Min Act: -0.0001

Data Index: 900041 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1487131 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.2103. Min Act: -0.0001

Data Index: 828096 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.1629. Min Act: -0.0001

Data Index: 902744 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.2025. Min Act: -0.0001

Data Index: 649224 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.1836. Min Act: -0.0001

Data Index: 1375994 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.2299. Min Act: -0.0001

Data Index: 1426535 (Python Code)

Max Activating Token Index: 212

Text #19

Max Range: 1.5148. Min Range: -1.5148

Max Act: 1.1390. Min Act: -0.0001

Data Index: 1333263 (C4 (Web Text))

Max Activating Token Index: 637