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

Dataset: The Pile

Neuron 4681 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1345037 (The Pile)

Max Activating Token Index: 933

Text #1

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.7674. Min Act: 0.0000

Data Index: 1137294 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.7638. Min Act: -0.0000

Data Index: 264174 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6333. Min Act: -0.0000

Data Index: 878704 (The Pile)

Max Activating Token Index: 802

Text #4

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.7583. Min Act: -0.0000

Data Index: 639553 (The Pile)

Max Activating Token Index: 958

Text #5

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1191840 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.7014. Min Act: -0.0000

Data Index: 198519 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6587. Min Act: -0.0000

Data Index: 551432 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6088. Min Act: -0.0000

Data Index: 658488 (The Pile)

Max Activating Token Index: 572

Text #9

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6594. Min Act: -0.0000

Data Index: 115253 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6472. Min Act: -0.0000

Data Index: 853298 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1352030 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5989. Min Act: 0.0000

Data Index: 669006 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1416574 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6086. Min Act: 0.0000

Data Index: 487079 (The Pile)

Max Activating Token Index: 429

Text #15

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6408. Min Act: -0.0000

Data Index: 372655 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5814. Min Act: -0.0000

Data Index: 200972 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1525200 (The Pile)

Max Activating Token Index: 1006

Text #18

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1089551 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5536. Min Act: -0.0000

Data Index: 55377 (The Pile)

Max Activating Token Index: 754