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

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

Neuron 1397 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: 1.4453. Min Range: -1.4453

Max Act: 1.3732. Min Act: -0.0000

Data Index: 1591871 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.4453. Min Act: -0.0000

Data Index: 1444347 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1475792 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.1788. Min Act: -0.0000

Data Index: 596824 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.2320. Min Act: -0.0000

Data Index: 61083 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1588035 (Python Code)

Max Activating Token Index: 410

Text #6

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1612492 (Python Code)

Max Activating Token Index: 626

Text #7

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1605914 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1136462 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.1061. Min Act: -0.0000

Data Index: 657119 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1573956 (Python Code)

Max Activating Token Index: 778

Text #11

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1582855 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0643. Min Act: -0.0000

Data Index: 1486896 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0816. Min Act: -0.0000

Data Index: 1436042 (Python Code)

Max Activating Token Index: 579

Text #14

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0451. Min Act: -0.0000

Data Index: 1630635 (Python Code)

Max Activating Token Index: 339

Text #15

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1386880 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9420. Min Act: -0.0000

Data Index: 42817 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1642094 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1529831 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1614924 (Python Code)

Max Activating Token Index: 339