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

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

Neuron 2029 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: 2.6746. Min Range: -2.6746

Max Act: 2.6746. Min Act: -0.0000

Data Index: 340390 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 2.6746. Min Range: -2.6746

Max Act: 2.6538. Min Act: -0.0000

Data Index: 754170 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 2.6746. Min Range: -2.6746

Max Act: 2.4170. Min Act: -0.0000

Data Index: 253407 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 2.6746. Min Range: -2.6746

Max Act: 2.4620. Min Act: -0.0000

Data Index: 418439 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 2.6746. Min Range: -2.6746

Max Act: 2.2337. Min Act: -0.0000

Data Index: 1147862 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 2.6746. Min Range: -2.6746

Max Act: 2.1548. Min Act: -0.0000

Data Index: 199490 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 2.6746. Min Range: -2.6746

Max Act: 2.1323. Min Act: -0.0000

Data Index: 298285 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 2.6746. Min Range: -2.6746

Max Act: 2.0133. Min Act: -0.0000

Data Index: 1318759 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 2.6746. Min Range: -2.6746

Max Act: 2.0425. Min Act: -0.0000

Data Index: 666565 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.8305. Min Act: -0.0000

Data Index: 256688 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.8080. Min Act: -0.0000

Data Index: 1039755 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.8231. Min Act: -0.0000

Data Index: 309713 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.9919. Min Act: -0.0000

Data Index: 655889 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.7988. Min Act: -0.0000

Data Index: 188213 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.8271. Min Act: -0.0000

Data Index: 1647937 (Python Code)

Max Activating Token Index: 475

Text #15

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.8543. Min Act: -0.0000

Data Index: 129688 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.8436. Min Act: -0.0000

Data Index: 793341 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.6918. Min Act: -0.0000

Data Index: 951917 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.7310. Min Act: -0.0000

Data Index: 601849 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 2.6746. Min Range: -2.6746

Max Act: 1.9104. Min Act: -0.0000

Data Index: 306422 (C4 (Web Text))

Max Activating Token Index: 771