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

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

Neuron 2571 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1577410 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1371460 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1605878 (Python Code)

Max Activating Token Index: 104

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1379062 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1394874 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1637096 (Python Code)

Max Activating Token Index: 839

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1652602 (Python Code)

Max Activating Token Index: 24

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1531955 (Python Code)

Max Activating Token Index: 755

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1608941 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1512448 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1598324 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1635366 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1561017 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1585571 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1572798 (Python Code)

Max Activating Token Index: 736

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1395836 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0203. Min Act: -0.0001

Data Index: 1638069 (Python Code)

Max Activating Token Index: 24

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1606933 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1584488 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0202. Min Act: -0.0001

Data Index: 1561458 (Python Code)

Max Activating Token Index: 96