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

Dataset: The Pile

Neuron 472 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: 0.1611. Min Range: -0.1611

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1139559 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1825529 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1779726 (The Pile)

Max Activating Token Index: 341

Text #3

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1340894 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1239. Min Act: -0.0000

Data Index: 1496942 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1280. Min Act: -0.0000

Data Index: 473684 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1131. Min Act: -0.0000

Data Index: 78983 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1558016 (The Pile)

Max Activating Token Index: 641

Text #8

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1269. Min Act: -0.0000

Data Index: 486251 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1804387 (The Pile)

Max Activating Token Index: 28

Text #10

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1783592 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1123. Min Act: -0.0000

Data Index: 691858 (The Pile)

Max Activating Token Index: 970

Text #12

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1161. Min Act: -0.0000

Data Index: 648554 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1121. Min Act: -0.0000

Data Index: 170175 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1474473 (The Pile)

Max Activating Token Index: 387

Text #15

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1208. Min Act: -0.0000

Data Index: 939854 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1149. Min Act: -0.0000

Data Index: 451355 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1124. Min Act: -0.0000

Data Index: 170883 (The Pile)

Max Activating Token Index: 953

Text #18

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1788830 (The Pile)

Max Activating Token Index: 872

Text #19

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1580363 (The Pile)

Max Activating Token Index: 58