Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 669 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.4979. Min Act: -0.0003

Data Index: 1653217 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.4007. Min Act: -0.0003

Data Index: 1440372 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.3843. Min Act: -0.0003

Data Index: 1543338 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.2377. Min Act: -0.0003

Data Index: 1393097 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.3113. Min Act: -0.0004

Data Index: 1404360 (Python Code)

Max Activating Token Index: 279

Text #5

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.2757. Min Act: -0.0003

Data Index: 1562488 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.2602. Min Act: -0.0003

Data Index: 1635266 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.2922. Min Act: -0.0003

Data Index: 1573333 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.1858. Min Act: -0.0003

Data Index: 1524701 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.0951. Min Act: -0.0003

Data Index: 1507289 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.1486. Min Act: -0.0003

Data Index: 1431133 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.1060. Min Act: -0.0003

Data Index: 1652657 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.1367. Min Act: -0.0003

Data Index: 1573324 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.0652. Min Act: -0.0003

Data Index: 1509281 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.0225. Min Act: -0.0003

Data Index: 1434236 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.0823. Min Act: -0.0003

Data Index: 1377846 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.1139. Min Act: -0.0003

Data Index: 1624150 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.0801. Min Act: -0.0003

Data Index: 1363851 (Python Code)

Max Activating Token Index: 94

Text #18

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.0447. Min Act: -0.0003

Data Index: 1549864 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 1.4979. Min Range: -1.4979

Max Act: 1.0447. Min Act: -0.0003

Data Index: 1631780 (Python Code)

Max Activating Token Index: 3