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

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

Neuron 5151 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1409327 (Python Code)

Max Activating Token Index: 1021

Text #1

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1384304 (Python Code)

Max Activating Token Index: 196

Text #2

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1379043 (Python Code)

Max Activating Token Index: 317

Text #3

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1458436 (Python Code)

Max Activating Token Index: 899

Text #4

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1429789 (Python Code)

Max Activating Token Index: 106

Text #5

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1409107 (Python Code)

Max Activating Token Index: 318

Text #6

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1511096 (Python Code)

Max Activating Token Index: 410

Text #7

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1496593 (Python Code)

Max Activating Token Index: 724

Text #8

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1558115 (Python Code)

Max Activating Token Index: 727

Text #9

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1407663 (Python Code)

Max Activating Token Index: 430

Text #10

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1582420 (Python Code)

Max Activating Token Index: 946

Text #11

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1453449 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1640332 (Python Code)

Max Activating Token Index: 956

Text #13

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1424182 (Python Code)

Max Activating Token Index: 772

Text #14

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1619513 (Python Code)

Max Activating Token Index: 443

Text #15

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1466369 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1549659 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1382175 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1557815 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1482159 (Python Code)

Max Activating Token Index: 607