Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2862 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1575. Min Act: -0.0000

Data Index: 175070 (The Pile)

Max Activating Token Index: 14

Text #1

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1494. Min Act: -0.0000

Data Index: 550660 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1375. Min Act: -0.0000

Data Index: 629216 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1141464 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1301. Min Act: -0.0000

Data Index: 288447 (The Pile)

Max Activating Token Index: 291

Text #5

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1974675 (The Pile)

Max Activating Token Index: 452

Text #6

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1273266 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1453702 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1733970 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1004005 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1857125 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1260. Min Act: -0.0000

Data Index: 379032 (The Pile)

Max Activating Token Index: 392

Text #12

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1216. Min Act: -0.0000

Data Index: 828112 (The Pile)

Max Activating Token Index: 78

Text #13

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1672393 (The Pile)

Max Activating Token Index: 865

Text #14

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1251. Min Act: -0.0000

Data Index: 956552 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1283181 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1313. Min Act: -0.0000

Data Index: 697500 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1226363 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1199290 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1742017 (The Pile)

Max Activating Token Index: 684