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

Dataset: The Pile

Neuron 977 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0000

Data Index: 955353 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0264. Min Act: -0.0000

Data Index: 55529 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1620658 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0256. Min Act: -0.0000

Data Index: 606015 (The Pile)

Max Activating Token Index: 981

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0238. Min Act: 0.0000

Data Index: 1430081 (The Pile)

Max Activating Token Index: 1000

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0239. Min Act: 0.0000

Data Index: 1073202 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0229. Min Act: 0.0000

Data Index: 1040493 (The Pile)

Max Activating Token Index: 1019

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0228. Min Act: 0.0000

Data Index: 591723 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0228. Min Act: -0.0000

Data Index: 1299570 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0226. Min Act: 0.0000

Data Index: 431911 (The Pile)

Max Activating Token Index: 974

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0225. Min Act: -0.0000

Data Index: 539663 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0222. Min Act: -0.0000

Data Index: 947314 (The Pile)

Max Activating Token Index: 996

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0222. Min Act: -0.0000

Data Index: 1937457 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0219. Min Act: 0.0000

Data Index: 1314684 (The Pile)

Max Activating Token Index: 1006

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0218. Min Act: -0.0000

Data Index: 123316 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0218. Min Act: 0.0000

Data Index: 1924640 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0218. Min Act: 0.0000

Data Index: 1417971 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0218. Min Act: -0.0000

Data Index: 80103 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0217. Min Act: -0.0000

Data Index: 974222 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0215. Min Act: -0.0000

Data Index: 371122 (The Pile)

Max Activating Token Index: 578