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

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

Neuron 1905 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4581. Min Range: -5.4581

Max Act: 5.4581. Min Act: -0.0000

Data Index: 541549 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 5.4581. Min Range: -5.4581

Max Act: 4.9956. Min Act: -0.0000

Data Index: 984404 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 5.4581. Min Range: -5.4581

Max Act: 4.6646. Min Act: -0.0000

Data Index: 1291874 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 5.4581. Min Range: -5.4581

Max Act: 4.2564. Min Act: -0.0000

Data Index: 1185818 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 5.4581. Min Range: -5.4581

Max Act: 4.2480. Min Act: -0.0000

Data Index: 1475438 (Python Code)

Max Activating Token Index: 756

Text #5

Max Range: 5.4581. Min Range: -5.4581

Max Act: 4.3256. Min Act: -0.0000

Data Index: 545657 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 5.4581. Min Range: -5.4581

Max Act: 4.1213. Min Act: -0.0000

Data Index: 160106 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 5.4581. Min Range: -5.4581

Max Act: 4.4966. Min Act: -0.0000

Data Index: 1449110 (Python Code)

Max Activating Token Index: 401

Text #8

Max Range: 5.4581. Min Range: -5.4581

Max Act: 4.3097. Min Act: -0.0000

Data Index: 1608447 (Python Code)

Max Activating Token Index: 677

Text #9

Max Range: 5.4581. Min Range: -5.4581

Max Act: 4.2354. Min Act: -0.0000

Data Index: 1420144 (Python Code)

Max Activating Token Index: 633

Text #10

Max Range: 5.4581. Min Range: -5.4581

Max Act: 3.9131. Min Act: -0.0000

Data Index: 1636877 (Python Code)

Max Activating Token Index: 397

Text #11

Max Range: 5.4581. Min Range: -5.4581

Max Act: 3.6910. Min Act: -0.0000

Data Index: 1436798 (Python Code)

Max Activating Token Index: 612

Text #12

Max Range: 5.4581. Min Range: -5.4581

Max Act: 4.0139. Min Act: -0.0000

Data Index: 1632489 (Python Code)

Max Activating Token Index: 707

Text #13

Max Range: 5.4581. Min Range: -5.4581

Max Act: 3.8556. Min Act: -0.0000

Data Index: 1592021 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 5.4581. Min Range: -5.4581

Max Act: 3.9916. Min Act: -0.0000

Data Index: 411316 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 5.4581. Min Range: -5.4581

Max Act: 3.8237. Min Act: -0.0000

Data Index: 1395483 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 5.4581. Min Range: -5.4581

Max Act: 3.7955. Min Act: -0.0000

Data Index: 1414839 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 5.4581. Min Range: -5.4581

Max Act: 3.8058. Min Act: -0.0000

Data Index: 1363990 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 5.4581. Min Range: -5.4581

Max Act: 3.6272. Min Act: -0.0000

Data Index: 1566214 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 5.4581. Min Range: -5.4581

Max Act: 3.7264. Min Act: -0.0000

Data Index: 639004 (C4 (Web Text))

Max Activating Token Index: 918