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

Dataset: The Pile

Neuron 4465 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1047351 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1560. Min Act: -0.0000

Data Index: 797578 (The Pile)

Max Activating Token Index: 214

Text #2

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1588. Min Act: -0.0000

Data Index: 621292 (The Pile)

Max Activating Token Index: 799

Text #3

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1527. Min Act: -0.0000

Data Index: 866736 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1528240 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1361. Min Act: -0.0000

Data Index: 396871 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1933205 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1426330 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1421. Min Act: -0.0000

Data Index: 891454 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1522801 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1409425 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1181575 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1352. Min Act: -0.0000

Data Index: 1128542 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1672004 (The Pile)

Max Activating Token Index: 912

Text #14

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1340. Min Act: -0.0000

Data Index: 140325 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1333. Min Act: -0.0000

Data Index: 830682 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1294212 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1861001 (The Pile)

Max Activating Token Index: 40

Text #18

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1290792 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1246216 (The Pile)

Max Activating Token Index: 882