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

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

Neuron 3400 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1088065 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1495548 (Python Code)

Max Activating Token Index: 140

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1104357 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1214194 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1064176 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1038375 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0328. Min Act: -0.0003

Data Index: 937506 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0330. Min Act: -0.0003

Data Index: 255182 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1655269 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1526126 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1464572 (Python Code)

Max Activating Token Index: 27

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0313. Min Act: -0.0003

Data Index: 601398 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0311. Min Act: -0.0003

Data Index: 524712 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0303. Min Act: -0.0002

Data Index: 908004 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0305. Min Act: -0.0002

Data Index: 680908 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1592863 (Python Code)

Max Activating Token Index: 412

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1475061 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1000207 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0300. Min Act: -0.0003

Data Index: 214733 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0297. Min Act: -0.0003

Data Index: 362909 (C4 (Web Text))

Max Activating Token Index: 891