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

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

Neuron 1598 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1621613 (Python Code)

Max Activating Token Index: 362

Text #1

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1647. Min Act: -0.0000

Data Index: 409430 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1630. Min Act: -0.0000

Data Index: 26007 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1386939 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1256634 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1272188 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1654788 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1167976 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1492156 (Python Code)

Max Activating Token Index: 637

Text #9

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1083275 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1135010 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1192. Min Act: -0.0000

Data Index: 715718 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1400215 (Python Code)

Max Activating Token Index: 696

Text #13

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1388970 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1254. Min Act: -0.0000

Data Index: 969702 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1597745 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1354010 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1233. Min Act: -0.0000

Data Index: 299661 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1159. Min Act: -0.0000

Data Index: 892210 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1161. Min Act: -0.0000

Data Index: 297277 (C4 (Web Text))

Max Activating Token Index: 240