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

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

Neuron 1845 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: 1.0947. Min Range: -1.0947

Max Act: 1.0814. Min Act: -0.0001

Data Index: 623872 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.0947. Min Range: -1.0947

Max Act: 1.0600. Min Act: -0.0001

Data Index: 1283253 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 1.0947. Min Range: -1.0947

Max Act: 1.0947. Min Act: -0.0000

Data Index: 286903 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8959. Min Act: -0.0001

Data Index: 690449 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8617. Min Act: -0.0001

Data Index: 195600 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9519. Min Act: -0.0001

Data Index: 903363 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8911. Min Act: -0.0001

Data Index: 222854 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.7453. Min Act: -0.0001

Data Index: 1249859 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8627. Min Act: -0.0001

Data Index: 479099 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9422. Min Act: -0.0001

Data Index: 412996 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8584. Min Act: -0.0001

Data Index: 1034741 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8520. Min Act: -0.0001

Data Index: 1264704 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8495. Min Act: -0.0001

Data Index: 579508 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8294. Min Act: -0.0001

Data Index: 790032 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8192. Min Act: -0.0001

Data Index: 444169 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8816. Min Act: -0.0001

Data Index: 334722 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8161. Min Act: -0.0001

Data Index: 611097 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8351. Min Act: -0.0001

Data Index: 284594 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.7355. Min Act: -0.0001

Data Index: 1198320 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.7896. Min Act: -0.0001

Data Index: 904769 (C4 (Web Text))

Max Activating Token Index: 866