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

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

Neuron 498 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.2124. Min Act: -0.0001

Data Index: 188512 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.0383. Min Act: -0.0001

Data Index: 572774 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.2229. Min Act: -0.0001

Data Index: 817123 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.1402. Min Act: -0.0001

Data Index: 616638 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.0902. Min Act: -0.0002

Data Index: 1092563 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.9429. Min Act: -0.0002

Data Index: 775715 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.9150. Min Act: -0.0001

Data Index: 841596 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.9572. Min Act: -0.0001

Data Index: 289945 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.0501. Min Act: -0.0002

Data Index: 1027317 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.0393. Min Act: -0.0001

Data Index: 1024947 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.0810. Min Act: -0.0001

Data Index: 197225 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.0135. Min Act: -0.0001

Data Index: 803791 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.9860. Min Act: -0.0001

Data Index: 535468 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.0362. Min Act: -0.0001

Data Index: 1296064 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.0239. Min Act: -0.0001

Data Index: 458014 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.9908. Min Act: -0.0002

Data Index: 1081805 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.9537. Min Act: -0.0001

Data Index: 652647 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.0106. Min Act: -0.0001

Data Index: 1073168 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.9306. Min Act: -0.0001

Data Index: 1459044 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.8264. Min Act: -0.0001

Data Index: 1181626 (C4 (Web Text))

Max Activating Token Index: 949