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

Dataset: The Pile

Neuron 4914 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: 0.1881. Min Range: -0.1881

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1691599 (The Pile)

Max Activating Token Index: 251

Text #1

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1526896 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1112443 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1443. Min Act: -0.0000

Data Index: 336259 (The Pile)

Max Activating Token Index: 299

Text #4

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1569668 (The Pile)

Max Activating Token Index: 588

Text #5

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1911890 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1237. Min Act: -0.0000

Data Index: 243505 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1406. Min Act: -0.0000

Data Index: 75477 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1286986 (The Pile)

Max Activating Token Index: 797

Text #9

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1524514 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1132. Min Act: -0.0000

Data Index: 774370 (The Pile)

Max Activating Token Index: 277

Text #11

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1388657 (The Pile)

Max Activating Token Index: 127

Text #12

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1263. Min Act: -0.0000

Data Index: 82461 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1144491 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1255. Min Act: -0.0000

Data Index: 389660 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1168. Min Act: -0.0000

Data Index: 613802 (The Pile)

Max Activating Token Index: 367

Text #16

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1249. Min Act: -0.0000

Data Index: 996076 (The Pile)

Max Activating Token Index: 743

Text #17

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1413218 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1261. Min Act: -0.0000

Data Index: 242492 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1567898 (The Pile)

Max Activating Token Index: 556