Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 816 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8385. Min Act: -0.0001

Data Index: 257523 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7745. Min Act: -0.0001

Data Index: 846978 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7447. Min Act: -0.0001

Data Index: 1554537 (Python Code)

Max Activating Token Index: 626

Text #3

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7301. Min Act: -0.0001

Data Index: 1176931 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7193. Min Act: -0.0001

Data Index: 170164 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7634. Min Act: -0.0001

Data Index: 285976 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7513. Min Act: -0.0001

Data Index: 490321 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6609. Min Act: -0.0001

Data Index: 1065607 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6908. Min Act: -0.0001

Data Index: 975274 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7207. Min Act: -0.0001

Data Index: 567436 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6930. Min Act: -0.0001

Data Index: 696719 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6851. Min Act: -0.0001

Data Index: 1638980 (Python Code)

Max Activating Token Index: 462

Text #12

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.5778. Min Act: -0.0001

Data Index: 1048386 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6310. Min Act: -0.0001

Data Index: 1500421 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6746. Min Act: -0.0001

Data Index: 1133955 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6262. Min Act: -0.0001

Data Index: 1088282 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6327. Min Act: -0.0001

Data Index: 1599077 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6891. Min Act: -0.0001

Data Index: 352426 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6465. Min Act: -0.0001

Data Index: 339637 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6031. Min Act: -0.0001

Data Index: 1298535 (C4 (Web Text))

Max Activating Token Index: 468