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

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

Neuron 1147 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: 0.0322. Min Range: -0.0322

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1396944 (Python Code)

Max Activating Token Index: 557

Text #1

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0305. Min Act: -0.0002

Data Index: 497501 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1041825 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0226. Min Act: -0.0002

Data Index: 454297 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0213. Min Act: -0.0002

Data Index: 670675 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0213. Min Act: -0.0002

Data Index: 499532 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0210. Min Act: -0.0002

Data Index: 703982 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1184517 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0201. Min Act: -0.0002

Data Index: 270558 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0204. Min Act: -0.0002

Data Index: 455072 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1097614 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1446009 (Python Code)

Max Activating Token Index: 920

Text #12

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1596629 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0198. Min Act: -0.0002

Data Index: 768229 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0196. Min Act: -0.0002

Data Index: 118513 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0192. Min Act: -0.0002

Data Index: 475789 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1561201 (Python Code)

Max Activating Token Index: 618

Text #17

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0187. Min Act: -0.0002

Data Index: 882955 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1431240 (Python Code)

Max Activating Token Index: 785

Text #19

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0186. Min Act: -0.0002

Data Index: 694390 (C4 (Web Text))

Max Activating Token Index: 438