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

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

Neuron 2359 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2376. Min Act: -0.0003

Data Index: 1499996 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2367. Min Act: -0.0003

Data Index: 1402179 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2510. Min Act: -0.0003

Data Index: 1479271 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2457. Min Act: -0.0003

Data Index: 1427634 (Python Code)

Max Activating Token Index: 769

Text #4

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2628. Min Act: -0.0003

Data Index: 1489246 (Python Code)

Max Activating Token Index: 612

Text #5

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2368. Min Act: -0.0003

Data Index: 1518242 (Python Code)

Max Activating Token Index: 215

Text #6

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2599. Min Act: -0.0003

Data Index: 1364129 (Python Code)

Max Activating Token Index: 859

Text #7

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2538. Min Act: -0.0003

Data Index: 1597350 (Python Code)

Max Activating Token Index: 918

Text #8

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2437. Min Act: -0.0003

Data Index: 1653132 (Python Code)

Max Activating Token Index: 693

Text #9

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2221. Min Act: -0.0003

Data Index: 1556460 (Python Code)

Max Activating Token Index: 1021

Text #10

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2468. Min Act: -0.0003

Data Index: 1519489 (Python Code)

Max Activating Token Index: 691

Text #11

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2222. Min Act: -0.0003

Data Index: 1651308 (Python Code)

Max Activating Token Index: 475

Text #12

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2194. Min Act: -0.0003

Data Index: 1486912 (Python Code)

Max Activating Token Index: 585

Text #13

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2142. Min Act: -0.0003

Data Index: 1654144 (Python Code)

Max Activating Token Index: 944

Text #14

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2285. Min Act: -0.0003

Data Index: 1541315 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2264. Min Act: -0.0003

Data Index: 1486308 (Python Code)

Max Activating Token Index: 222

Text #16

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2114. Min Act: -0.0003

Data Index: 1588728 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2155. Min Act: -0.0003

Data Index: 1643356 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2192. Min Act: -0.0003

Data Index: 1390133 (Python Code)

Max Activating Token Index: 566

Text #19

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2128. Min Act: -0.0003

Data Index: 1647588 (Python Code)

Max Activating Token Index: 484