Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 491 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1068514 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1704. Min Act: -0.0000

Data Index: 403991 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1655536 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1392474 (The Pile)

Max Activating Token Index: 970

Text #4

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1161070 (The Pile)

Max Activating Token Index: 596

Text #5

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1380880 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1838777 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1324932 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1629518 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1092807 (The Pile)

Max Activating Token Index: 917

Text #10

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1656980 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1444. Min Act: -0.0000

Data Index: 175955 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1166. Min Act: -0.0000

Data Index: 790610 (The Pile)

Max Activating Token Index: 866

Text #13

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1269720 (The Pile)

Max Activating Token Index: 438

Text #14

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1401. Min Act: -0.0000

Data Index: 975600 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1263. Min Act: -0.0000

Data Index: 784300 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1253. Min Act: -0.0000

Data Index: 274851 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1121163 (The Pile)

Max Activating Token Index: 9

Text #18

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1216. Min Act: -0.0000

Data Index: 368690 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1214. Min Act: -0.0000

Data Index: 795194 (The Pile)

Max Activating Token Index: 128