Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3663 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2619. Min Act: -0.0001

Data Index: 658663 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2744. Min Act: -0.0001

Data Index: 1010769 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2563. Min Act: -0.0001

Data Index: 1540506 (Python Code)

Max Activating Token Index: 660

Text #3

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2529. Min Act: -0.0001

Data Index: 1571854 (Python Code)

Max Activating Token Index: 830

Text #4

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1242736 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2233. Min Act: -0.0001

Data Index: 684287 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2244. Min Act: -0.0001

Data Index: 944481 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1627388 (Python Code)

Max Activating Token Index: 667

Text #8

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2082. Min Act: -0.0000

Data Index: 275030 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2317. Min Act: -0.0001

Data Index: 280907 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2188. Min Act: -0.0001

Data Index: 127482 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2165. Min Act: -0.0000

Data Index: 651873 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2057. Min Act: -0.0000

Data Index: 171808 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2174. Min Act: -0.0000

Data Index: 486214 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2020. Min Act: -0.0000

Data Index: 113583 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1036312 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2009. Min Act: -0.0000

Data Index: 301411 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1992. Min Act: -0.0000

Data Index: 34305 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2033. Min Act: -0.0000

Data Index: 107618 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2029. Min Act: -0.0001

Data Index: 18091 (C4 (Web Text))

Max Activating Token Index: 565