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

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

Neuron 375 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.7225. Min Act: -0.0000

Data Index: 316434 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.6401. Min Act: 0.0003

Data Index: 920903 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.6580. Min Act: -0.0000

Data Index: 645462 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.6524. Min Act: -0.0000

Data Index: 530829 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.6251. Min Act: -0.0000

Data Index: 398419 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1149748 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.6578. Min Act: -0.0000

Data Index: 379855 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.6237. Min Act: -0.0000

Data Index: 10404 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1173760 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5781. Min Act: 0.0000

Data Index: 1006363 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5701. Min Act: 0.0002

Data Index: 408256 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5678. Min Act: -0.0000

Data Index: 269201 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5459. Min Act: -0.0000

Data Index: 873600 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5463. Min Act: -0.0000

Data Index: 667884 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5359. Min Act: -0.0000

Data Index: 381838 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1276857 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5307. Min Act: -0.0000

Data Index: 816154 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1310148 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5308. Min Act: 0.0004

Data Index: 456099 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.7225. Min Range: -0.7225

Max Act: 0.5238. Min Act: -0.0000

Data Index: 9748 (C4 (Web Text))

Max Activating Token Index: 922