Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2594 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0004

Data Index: 1364116 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0273. Min Act: -0.0004

Data Index: 1476162 (Python Code)

Max Activating Token Index: 533

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1618712 (Python Code)

Max Activating Token Index: 412

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0242. Min Act: -0.0004

Data Index: 1553754 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0220. Min Act: -0.0004

Data Index: 1649180 (Python Code)

Max Activating Token Index: 922

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0255. Min Act: -0.0004

Data Index: 1569074 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0201. Min Act: -0.0004

Data Index: 1577107 (Python Code)

Max Activating Token Index: 685

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1435244 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0209. Min Act: -0.0004

Data Index: 1574729 (Python Code)

Max Activating Token Index: 621

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0210. Min Act: -0.0004

Data Index: 1629024 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1462434 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0213. Min Act: -0.0004

Data Index: 1576724 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0188. Min Act: -0.0004

Data Index: 1520464 (Python Code)

Max Activating Token Index: 689

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0183. Min Act: -0.0004

Data Index: 1557801 (Python Code)

Max Activating Token Index: 287

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0201. Min Act: -0.0004

Data Index: 1496055 (Python Code)

Max Activating Token Index: 497

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0212. Min Act: -0.0004

Data Index: 1656644 (Python Code)

Max Activating Token Index: 430

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0207. Min Act: -0.0004

Data Index: 1568426 (Python Code)

Max Activating Token Index: 56

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0215. Min Act: -0.0004

Data Index: 1372912 (Python Code)

Max Activating Token Index: 168

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0235. Min Act: -0.0004

Data Index: 1400117 (Python Code)

Max Activating Token Index: 823

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0205. Min Act: -0.0004

Data Index: 1452639 (Python Code)

Max Activating Token Index: 50