Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5985 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1733. Min Act: -0.0001

Data Index: 459732 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1879. Min Act: -0.0001

Data Index: 241260 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1450. Min Act: -0.0001

Data Index: 612509 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1301. Min Act: -0.0001

Data Index: 227891 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1188300 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1459. Min Act: -0.0001

Data Index: 509785 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1278. Min Act: -0.0001

Data Index: 461444 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1272. Min Act: -0.0001

Data Index: 913086 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1233544 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1138. Min Act: -0.0001

Data Index: 759371 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1139156 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1228. Min Act: -0.0001

Data Index: 617590 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1324019 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1108. Min Act: -0.0001

Data Index: 885094 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.0837. Min Act: -0.0001

Data Index: 633876 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1496666 (Python Code)

Max Activating Token Index: 412

Text #16

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1230. Min Act: -0.0001

Data Index: 732659 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1092. Min Act: -0.0001

Data Index: 722531 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1129. Min Act: -0.0001

Data Index: 351094 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1211. Min Act: -0.0001

Data Index: 750317 (C4 (Web Text))

Max Activating Token Index: 666