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

Dataset: The Pile

Neuron 2866 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: 0.7618. Min Range: -0.7618

Max Act: 0.7618. Min Act: -0.0000

Data Index: 62726 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6887. Min Act: -0.0000

Data Index: 104268 (The Pile)

Max Activating Token Index: 509

Text #2

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1775515 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1367221 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1467480 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5318. Min Act: -0.0000

Data Index: 148676 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5203. Min Act: -0.0000

Data Index: 667371 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1199126 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5158. Min Act: -0.0000

Data Index: 942492 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.4479. Min Act: -0.0000

Data Index: 749414 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5071. Min Act: -0.0000

Data Index: 117658 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5265. Min Act: -0.0000

Data Index: 565079 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.4817. Min Act: -0.0000

Data Index: 688180 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.4050. Min Act: -0.0000

Data Index: 704518 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1410565 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.4103. Min Act: -0.0000

Data Index: 315478 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.4627. Min Act: -0.0000

Data Index: 159022 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.4555. Min Act: -0.0000

Data Index: 905139 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.3938. Min Act: -0.0000

Data Index: 895857 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1270098 (The Pile)

Max Activating Token Index: 104