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

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

Neuron 2013 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4612. Min Range: -6.4612

Max Act: 6.4612. Min Act: -0.0000

Data Index: 998873 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 6.4612. Min Range: -6.4612

Max Act: 5.7792. Min Act: -0.0000

Data Index: 848828 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 6.4612. Min Range: -6.4612

Max Act: 5.3643. Min Act: -0.0000

Data Index: 1178959 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 6.4612. Min Range: -6.4612

Max Act: 5.6547. Min Act: -0.0000

Data Index: 1009272 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.4598. Min Act: -0.0000

Data Index: 361961 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 6.4612. Min Range: -6.4612

Max Act: 5.1453. Min Act: -0.0000

Data Index: 675633 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.7617. Min Act: -0.0001

Data Index: 270146 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.8599. Min Act: -0.0001

Data Index: 943583 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 6.4612. Min Range: -6.4612

Max Act: 5.0219. Min Act: -0.0000

Data Index: 1354301 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.8989. Min Act: -0.0000

Data Index: 446239 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.5877. Min Act: -0.0000

Data Index: 743374 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.4624. Min Act: -0.0000

Data Index: 1008597 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.1146. Min Act: -0.0000

Data Index: 183434 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 6.4612. Min Range: -6.4612

Max Act: 3.9852. Min Act: -0.0000

Data Index: 1318188 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.1284. Min Act: -0.0000

Data Index: 347107 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.0429. Min Act: -0.0001

Data Index: 1113043 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.4052. Min Act: -0.0000

Data Index: 13984 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.0127. Min Act: -0.0000

Data Index: 1226787 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 6.4612. Min Range: -6.4612

Max Act: 4.6372. Min Act: -0.0000

Data Index: 391717 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 6.4612. Min Range: -6.4612

Max Act: 3.8814. Min Act: -0.0000

Data Index: 972362 (C4 (Web Text))

Max Activating Token Index: 512