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

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

Neuron 3423 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: 2.1284. Min Range: -2.1284

Max Act: 2.1284. Min Act: -0.0000

Data Index: 1405931 (Python Code)

Max Activating Token Index: 675

Text #1

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1421393 (Python Code)

Max Activating Token Index: 255

Text #2

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.5884. Min Act: -0.0000

Data Index: 1640339 (Python Code)

Max Activating Token Index: 998

Text #3

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.6085. Min Act: -0.0001

Data Index: 1595189 (Python Code)

Max Activating Token Index: 227

Text #4

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1600220 (Python Code)

Max Activating Token Index: 296

Text #5

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.4129. Min Act: -0.0001

Data Index: 1405213 (Python Code)

Max Activating Token Index: 401

Text #6

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.3830. Min Act: -0.0001

Data Index: 1498233 (Python Code)

Max Activating Token Index: 919

Text #7

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.4627. Min Act: -0.0000

Data Index: 1421898 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.4105. Min Act: -0.0000

Data Index: 1543954 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.4256. Min Act: -0.0001

Data Index: 1480768 (Python Code)

Max Activating Token Index: 712

Text #10

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.3691. Min Act: -0.0001

Data Index: 1539297 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.3157. Min Act: -0.0001

Data Index: 1607007 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.3732. Min Act: -0.0000

Data Index: 1642014 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.4077. Min Act: -0.0000

Data Index: 1624284 (Python Code)

Max Activating Token Index: 519

Text #14

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.4136. Min Act: -0.0000

Data Index: 1581225 (Python Code)

Max Activating Token Index: 541

Text #15

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.3353. Min Act: -0.0001

Data Index: 1587401 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.4084. Min Act: -0.0000

Data Index: 1463776 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.2625. Min Act: -0.0000

Data Index: 1520503 (Python Code)

Max Activating Token Index: 1014

Text #18

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.3631. Min Act: -0.0001

Data Index: 1542624 (Python Code)

Max Activating Token Index: 988

Text #19

Max Range: 2.1284. Min Range: -2.1284

Max Act: 1.3646. Min Act: -0.0000

Data Index: 1397755 (Python Code)

Max Activating Token Index: 162