Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 601 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0287. Min Act: -0.0003

Data Index: 34910 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1492056 (Python Code)

Max Activating Token Index: 979

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1072328 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0276. Min Act: -0.0003

Data Index: 335081 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1288207 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0278. Min Act: -0.0003

Data Index: 391977 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0272. Min Act: -0.0003

Data Index: 671984 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0283. Min Act: -0.0004

Data Index: 218202 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1012532 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0261. Min Act: -0.0004

Data Index: 1580556 (Python Code)

Max Activating Token Index: 991

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0274. Min Act: -0.0003

Data Index: 92139 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0267. Min Act: -0.0004

Data Index: 600055 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0261. Min Act: -0.0003

Data Index: 4555 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0272. Min Act: -0.0003

Data Index: 41837 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1086995 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0269. Min Act: -0.0003

Data Index: 970305 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0273. Min Act: -0.0003

Data Index: 314139 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0256. Min Act: -0.0003

Data Index: 861800 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0262. Min Act: -0.0003

Data Index: 600775 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0263. Min Act: -0.0004

Data Index: 714691 (C4 (Web Text))

Max Activating Token Index: 746