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

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

Neuron 5607 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1462928 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.3324. Min Act: -0.0000

Data Index: 1656075 (Python Code)

Max Activating Token Index: 287

Text #2

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.4933. Min Act: -0.0000

Data Index: 1525101 (Python Code)

Max Activating Token Index: 442

Text #3

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1438084 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1469923 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1372822 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1534699 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.2745. Min Act: -0.0000

Data Index: 1554344 (Python Code)

Max Activating Token Index: 400

Text #8

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.2673. Min Act: -0.0000

Data Index: 1532282 (Python Code)

Max Activating Token Index: 460

Text #9

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.2617. Min Act: -0.0000

Data Index: 1423514 (Python Code)

Max Activating Token Index: 382

Text #10

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1550120 (Python Code)

Max Activating Token Index: 533

Text #11

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1440160 (Python Code)

Max Activating Token Index: 629

Text #12

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1397286 (Python Code)

Max Activating Token Index: 654

Text #13

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1581847 (Python Code)

Max Activating Token Index: 618

Text #14

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.0836. Min Act: -0.0000

Data Index: 1652478 (Python Code)

Max Activating Token Index: 774

Text #15

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1196. Min Act: -0.0000

Data Index: 1529842 (Python Code)

Max Activating Token Index: 533

Text #16

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1607259 (Python Code)

Max Activating Token Index: 742

Text #17

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1765. Min Act: -0.0000

Data Index: 1452858 (Python Code)

Max Activating Token Index: 848

Text #18

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1550746 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1114. Min Act: -0.0000

Data Index: 1536812 (Python Code)

Max Activating Token Index: 641