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

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

Neuron 3259 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0116. Min Range: -1.0116

Max Act: 1.0116. Min Act: -0.0001

Data Index: 1062614 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8147. Min Act: -0.0001

Data Index: 993867 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.9232. Min Act: -0.0001

Data Index: 1207785 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7989. Min Act: -0.0001

Data Index: 1233490 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7715. Min Act: -0.0001

Data Index: 1554497 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1605874 (Python Code)

Max Activating Token Index: 988

Text #6

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8406. Min Act: -0.0001

Data Index: 551677 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8196. Min Act: -0.0001

Data Index: 698173 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7919. Min Act: -0.0001

Data Index: 1250124 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7891. Min Act: -0.0001

Data Index: 223967 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8062. Min Act: -0.0001

Data Index: 650804 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7840. Min Act: -0.0001

Data Index: 1267853 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8032. Min Act: -0.0000

Data Index: 7824 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7395. Min Act: -0.0001

Data Index: 1499218 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7772. Min Act: -0.0001

Data Index: 1323980 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7823. Min Act: -0.0001

Data Index: 599096 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7751. Min Act: -0.0001

Data Index: 740248 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8229. Min Act: -0.0001

Data Index: 1292010 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7501. Min Act: -0.0001

Data Index: 835490 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7702. Min Act: -0.0001

Data Index: 964545 (C4 (Web Text))

Max Activating Token Index: 986