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

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

Neuron 3330 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2086. Min Range: -3.2086

Max Act: 3.2086. Min Act: -0.0000

Data Index: 1641446 (Python Code)

Max Activating Token Index: 323

Text #1

Max Range: 3.2086. Min Range: -3.2086

Max Act: 3.1004. Min Act: -0.0000

Data Index: 1388318 (Python Code)

Max Activating Token Index: 702

Text #2

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.7941. Min Act: -0.0000

Data Index: 1370334 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.9221. Min Act: -0.0000

Data Index: 1379584 (Python Code)

Max Activating Token Index: 106

Text #4

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.8001. Min Act: -0.0000

Data Index: 1634332 (Python Code)

Max Activating Token Index: 562

Text #5

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.6184. Min Act: -0.0000

Data Index: 1488341 (Python Code)

Max Activating Token Index: 358

Text #6

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.7662. Min Act: -0.0000

Data Index: 1600566 (Python Code)

Max Activating Token Index: 286

Text #7

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.7331. Min Act: -0.0000

Data Index: 1554402 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.6328. Min Act: -0.0000

Data Index: 1469051 (Python Code)

Max Activating Token Index: 466

Text #9

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.5095. Min Act: -0.0000

Data Index: 1385693 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.6344. Min Act: -0.0000

Data Index: 1540421 (Python Code)

Max Activating Token Index: 376

Text #11

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.6558. Min Act: -0.0000

Data Index: 1434799 (Python Code)

Max Activating Token Index: 337

Text #12

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.6571. Min Act: -0.0000

Data Index: 1418428 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.5251. Min Act: -0.0000

Data Index: 1511737 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.3631. Min Act: -0.0000

Data Index: 1518784 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.4803. Min Act: -0.0000

Data Index: 1536591 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.4821. Min Act: -0.0000

Data Index: 1370941 (Python Code)

Max Activating Token Index: 598

Text #17

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.4518. Min Act: -0.0000

Data Index: 1635859 (Python Code)

Max Activating Token Index: 874

Text #18

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.3363. Min Act: -0.0000

Data Index: 1577819 (Python Code)

Max Activating Token Index: 384

Text #19

Max Range: 3.2086. Min Range: -3.2086

Max Act: 2.2668. Min Act: -0.0000

Data Index: 1643411 (Python Code)

Max Activating Token Index: 795