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

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

Neuron 157 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.7370. Min Act: -0.0001

Data Index: 443578 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.6735. Min Act: -0.0001

Data Index: 289664 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5487. Min Act: -0.0001

Data Index: 722624 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5343. Min Act: -0.0001

Data Index: 697577 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5432. Min Act: -0.0002

Data Index: 185231 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5582. Min Act: -0.0002

Data Index: 442628 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5286. Min Act: -0.0002

Data Index: 540514 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5138. Min Act: -0.0002

Data Index: 386663 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4925. Min Act: -0.0001

Data Index: 32675 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4561. Min Act: -0.0001

Data Index: 1375344 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5247. Min Act: -0.0002

Data Index: 1316087 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4908. Min Act: -0.0001

Data Index: 112896 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4795. Min Act: -0.0001

Data Index: 248578 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4766. Min Act: -0.0002

Data Index: 977228 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4600. Min Act: -0.0002

Data Index: 848929 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4784. Min Act: -0.0001

Data Index: 615895 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4518. Min Act: -0.0002

Data Index: 498716 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4636. Min Act: -0.0002

Data Index: 734737 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4886. Min Act: -0.0001

Data Index: 361405 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4693. Min Act: -0.0002

Data Index: 925923 (C4 (Web Text))

Max Activating Token Index: 68