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

Dataset: The Pile

Neuron 2257 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: 0.2103. Min Range: -0.2103

Max Act: 0.2103. Min Act: -0.0000

Data Index: 497543 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.2032. Min Act: -0.0000

Data Index: 162227 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1762. Min Act: -0.0000

Data Index: 824695 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1841. Min Act: -0.0000

Data Index: 471558 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1563. Min Act: -0.0000

Data Index: 50283 (The Pile)

Max Activating Token Index: 295

Text #5

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1475. Min Act: -0.0000

Data Index: 19055 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1908664 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1516371 (The Pile)

Max Activating Token Index: 196

Text #8

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1383. Min Act: -0.0000

Data Index: 624800 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1448. Min Act: -0.0000

Data Index: 621590 (The Pile)

Max Activating Token Index: 161

Text #10

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1169602 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1411. Min Act: -0.0000

Data Index: 772330 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1403. Min Act: -0.0000

Data Index: 952564 (The Pile)

Max Activating Token Index: 193

Text #13

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1075149 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1465303 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1086186 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1681389 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1674237 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1423442 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1377. Min Act: -0.0000

Data Index: 221017 (The Pile)

Max Activating Token Index: 190