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

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

Neuron 3429 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1384089 (Python Code)

Max Activating Token Index: 400

Text #1

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1087787 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.6116. Min Act: -0.0000

Data Index: 561662 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1302364 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1044075 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4979. Min Act: -0.0000

Data Index: 272474 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4945. Min Act: -0.0000

Data Index: 135941 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1108012 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1248401 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1186185 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.5042. Min Act: -0.0000

Data Index: 743311 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1640010 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1028362 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4321. Min Act: -0.0000

Data Index: 599105 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4339. Min Act: -0.0000

Data Index: 317706 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1431741 (Python Code)

Max Activating Token Index: 251

Text #16

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1369026 (Python Code)

Max Activating Token Index: 439

Text #17

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1032086 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4156. Min Act: -0.0000

Data Index: 872151 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.6116. Min Range: -0.6116

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1441058 (Python Code)

Max Activating Token Index: 451