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

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

Neuron 960 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.2065. Min Range: -3.2065

Max Act: 3.2065. Min Act: -0.0002

Data Index: 1136890 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 3.2065. Min Range: -3.2065

Max Act: 3.1156. Min Act: -0.0002

Data Index: 895248 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 3.2065. Min Range: -3.2065

Max Act: 3.1402. Min Act: -0.0002

Data Index: 1113480 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 3.2065. Min Range: -3.2065

Max Act: 3.1045. Min Act: -0.0002

Data Index: 262813 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.9177. Min Act: -0.0002

Data Index: 439176 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.9782. Min Act: -0.0002

Data Index: 738070 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.9085. Min Act: -0.0002

Data Index: 461771 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.9602. Min Act: -0.0002

Data Index: 1073605 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.8664. Min Act: -0.0002

Data Index: 991250 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.9188. Min Act: -0.0002

Data Index: 962290 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.8163. Min Act: -0.0002

Data Index: 169793 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.9392. Min Act: -0.0002

Data Index: 169998 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.8759. Min Act: -0.0002

Data Index: 973340 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.8408. Min Act: -0.0002

Data Index: 971236 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.8855. Min Act: -0.0002

Data Index: 968855 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.8426. Min Act: -0.0002

Data Index: 932953 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.8106. Min Act: -0.0002

Data Index: 1314847 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.8987. Min Act: -0.0002

Data Index: 811007 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.8121. Min Act: -0.0002

Data Index: 525679 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 3.2065. Min Range: -3.2065

Max Act: 2.8492. Min Act: -0.0002

Data Index: 852471 (C4 (Web Text))

Max Activating Token Index: 175