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

Dataset: The Pile

Neuron 559 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: 1.0681. Min Range: -1.0681

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1814615 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 1.0681. Min Range: -1.0681

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1290996 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1149075 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1285305 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 1.0681. Min Range: -1.0681

Max Act: 1.0025. Min Act: -0.0000

Data Index: 946852 (The Pile)

Max Activating Token Index: 898

Text #5

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1247261 (The Pile)

Max Activating Token Index: 738

Text #6

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1590434 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1963683 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1506401 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1148140 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8989. Min Act: -0.0000

Data Index: 348452 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9157. Min Act: -0.0000

Data Index: 952264 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8314. Min Act: -0.0000

Data Index: 576848 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1823101 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8307. Min Act: -0.0000

Data Index: 382191 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8174. Min Act: -0.0000

Data Index: 648565 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1226678 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1652930 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8717. Min Act: -0.0000

Data Index: 706775 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7891. Min Act: -0.0000

Data Index: 473024 (The Pile)

Max Activating Token Index: 71