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

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

Neuron 6121 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.2928. Min Act: -0.0000

Data Index: 1448026 (Python Code)

Max Activating Token Index: 499

Text #1

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.8510. Min Act: -0.0000

Data Index: 1428627 (Python Code)

Max Activating Token Index: 606

Text #2

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.9006. Min Act: -0.0000

Data Index: 1379186 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.9119. Min Act: -0.0000

Data Index: 1644573 (Python Code)

Max Activating Token Index: 98

Text #4

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.8532. Min Act: -0.0000

Data Index: 1389224 (Python Code)

Max Activating Token Index: 426

Text #5

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.8194. Min Act: -0.0000

Data Index: 1418349 (Python Code)

Max Activating Token Index: 627

Text #6

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.9898. Min Act: -0.0000

Data Index: 1407879 (Python Code)

Max Activating Token Index: 258

Text #7

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.7828. Min Act: -0.0000

Data Index: 1624824 (Python Code)

Max Activating Token Index: 379

Text #8

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.7945. Min Act: -0.0000

Data Index: 1366312 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.6558. Min Act: -0.0000

Data Index: 1509862 (Python Code)

Max Activating Token Index: 981

Text #10

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.0235. Min Act: -0.0000

Data Index: 1574482 (Python Code)

Max Activating Token Index: 982

Text #11

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.8818. Min Act: -0.0000

Data Index: 1417089 (Python Code)

Max Activating Token Index: 687

Text #12

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1519328 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.5617. Min Act: -0.0000

Data Index: 1408770 (Python Code)

Max Activating Token Index: 207

Text #14

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.5590. Min Act: -0.0000

Data Index: 1527689 (Python Code)

Max Activating Token Index: 1020

Text #15

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.7281. Min Act: -0.0000

Data Index: 1652217 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.5187. Min Act: -0.0000

Data Index: 985778 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.6821. Min Act: -0.0000

Data Index: 1386859 (Python Code)

Max Activating Token Index: 670

Text #18

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.5045. Min Act: -0.0000

Data Index: 1571615 (Python Code)

Max Activating Token Index: 729

Text #19

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.5820. Min Act: -0.0000

Data Index: 1406382 (Python Code)

Max Activating Token Index: 210