Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 13 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0150. Min Act: -0.0002

Data Index: 419618 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0136. Min Act: -0.0002

Data Index: 388423 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0131. Min Act: -0.0002

Data Index: 375062 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0128. Min Act: -0.0002

Data Index: 641277 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0126. Min Act: -0.0002

Data Index: 762103 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0126. Min Act: -0.0002

Data Index: 300425 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0123. Min Act: -0.0002

Data Index: 976844 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0125. Min Act: -0.0003

Data Index: 140017 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0122. Min Act: -0.0002

Data Index: 64978 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1449160 (Python Code)

Max Activating Token Index: 971

Text #10

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1615043 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0117. Min Act: -0.0002

Data Index: 465237 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1548345 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1260723 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0118. Min Act: -0.0003

Data Index: 778082 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0118. Min Act: -0.0002

Data Index: 133228 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1110252 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1022077 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0116. Min Act: -0.0002

Data Index: 652456 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1221421 (C4 (Web Text))

Max Activating Token Index: 490