Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2036 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0364. Min Act: -0.0001

Data Index: 204737 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0370. Min Act: -0.0001

Data Index: 698433 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0352. Min Act: -0.0001

Data Index: 563452 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0001

Data Index: 782669 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0349. Min Act: -0.0001

Data Index: 418925 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1136620 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0337. Min Act: -0.0001

Data Index: 91081 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0340. Min Act: -0.0001

Data Index: 424737 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0334. Min Act: -0.0001

Data Index: 843641 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1507028 (Python Code)

Max Activating Token Index: 174

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0327. Min Act: -0.0001

Data Index: 912442 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0316. Min Act: -0.0001

Data Index: 379978 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1349659 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0322. Min Act: -0.0001

Data Index: 621752 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1168103 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0310. Min Act: -0.0001

Data Index: 579754 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0318. Min Act: -0.0001

Data Index: 837856 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0284. Min Act: -0.0001

Data Index: 138446 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0311. Min Act: -0.0001

Data Index: 838737 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1055628 (C4 (Web Text))

Max Activating Token Index: 28