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

Dataset: The Pile

Neuron 1458 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.7412. Min Act: 0.0000

Data Index: 524066 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.6913. Min Act: -0.0000

Data Index: 450048 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1130775 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.6358. Min Act: -0.0000

Data Index: 292268 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1413678 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.6147. Min Act: 0.0000

Data Index: 1230611 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1834606 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5602. Min Act: 0.0000

Data Index: 1261652 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1107441 (The Pile)

Max Activating Token Index: 603

Text #9

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5401. Min Act: 0.0000

Data Index: 1479320 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5149. Min Act: -0.0000

Data Index: 69650 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5235. Min Act: -0.0000

Data Index: 520077 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1219486 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1462485 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1284754 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5359. Min Act: -0.0000

Data Index: 466488 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1169390 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5006. Min Act: 0.0000

Data Index: 729813 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1820898 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1258821 (The Pile)

Max Activating Token Index: 454