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

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

Neuron 3685 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1382110 (Python Code)

Max Activating Token Index: 597

Text #1

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1654035 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1541947 (Python Code)

Max Activating Token Index: 697

Text #3

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1373838 (Python Code)

Max Activating Token Index: 225

Text #4

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1548174 (Python Code)

Max Activating Token Index: 880

Text #5

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1575896 (Python Code)

Max Activating Token Index: 751

Text #6

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1558898 (Python Code)

Max Activating Token Index: 834

Text #7

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1460766 (Python Code)

Max Activating Token Index: 986

Text #8

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1647174 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1612163 (Python Code)

Max Activating Token Index: 1000

Text #10

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1387725 (Python Code)

Max Activating Token Index: 699

Text #11

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1463160 (Python Code)

Max Activating Token Index: 242

Text #12

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1627751 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1550717 (Python Code)

Max Activating Token Index: 570

Text #14

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1457152 (Python Code)

Max Activating Token Index: 147

Text #15

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1541281 (Python Code)

Max Activating Token Index: 633

Text #16

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1533972 (Python Code)

Max Activating Token Index: 976

Text #17

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1635123 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1367588 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1603158 (Python Code)

Max Activating Token Index: 827