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

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

Neuron 3134 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1642644 (Python Code)

Max Activating Token Index: 1012

Text #1

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1391926 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1134850 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1184691 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1006272 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1227. Min Act: -0.0000

Data Index: 868333 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1186960 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1231. Min Act: -0.0000

Data Index: 75764 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1139040 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1469379 (Python Code)

Max Activating Token Index: 404

Text #10

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1214. Min Act: -0.0000

Data Index: 794842 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1168. Min Act: -0.0000

Data Index: 656011 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1191. Min Act: -0.0000

Data Index: 691525 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1567023 (Python Code)

Max Activating Token Index: 1022

Text #14

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1485307 (Python Code)

Max Activating Token Index: 545

Text #15

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1207731 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1129. Min Act: -0.0000

Data Index: 195259 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1521150 (Python Code)

Max Activating Token Index: 843

Text #18

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1084678 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1512398 (Python Code)

Max Activating Token Index: 650