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

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

Neuron 1912 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: 0.0400. Min Range: -0.0400

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1317519 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0340. Min Act: -0.0002

Data Index: 264436 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0341. Min Act: -0.0002

Data Index: 428871 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0299. Min Act: -0.0003

Data Index: 693561 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0294. Min Act: -0.0003

Data Index: 479356 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0285. Min Act: -0.0003

Data Index: 534339 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1297694 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0263. Min Act: -0.0002

Data Index: 265160 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0277. Min Act: -0.0003

Data Index: 902296 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0274. Min Act: -0.0003

Data Index: 314116 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0275. Min Act: -0.0003

Data Index: 907622 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0267. Min Act: -0.0002

Data Index: 700534 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1174511 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0263. Min Act: -0.0002

Data Index: 687337 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0268. Min Act: -0.0003

Data Index: 940691 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0269. Min Act: -0.0003

Data Index: 321589 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0280. Min Act: -0.0003

Data Index: 237230 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0265. Min Act: -0.0003

Data Index: 828021 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0262. Min Act: -0.0002

Data Index: 183976 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0260. Min Act: -0.0003

Data Index: 128291 (C4 (Web Text))

Max Activating Token Index: 42