Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3381 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.1054. Min Act: -0.0000

Data Index: 658836 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.1313. Min Act: -0.0000

Data Index: 1205339 (The Pile)

Max Activating Token Index: 575

Text #2

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1851251 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1414764 (The Pile)

Max Activating Token Index: 390

Text #4

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0016. Min Act: -0.0000

Data Index: 257578 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0966. Min Act: -0.0000

Data Index: 454860 (The Pile)

Max Activating Token Index: 492

Text #6

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0008. Min Act: -0.0000

Data Index: 350087 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1646159 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9512. Min Act: -0.0000

Data Index: 290683 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1638612 (The Pile)

Max Activating Token Index: 305

Text #10

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1704793 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9574. Min Act: -0.0000

Data Index: 1304308 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9998. Min Act: -0.0000

Data Index: 579864 (The Pile)

Max Activating Token Index: 510

Text #13

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0360. Min Act: -0.0000

Data Index: 410950 (The Pile)

Max Activating Token Index: 201

Text #14

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9733. Min Act: -0.0000

Data Index: 290643 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9539. Min Act: -0.0000

Data Index: 149969 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1060119 (The Pile)

Max Activating Token Index: 487

Text #17

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9431. Min Act: -0.0000

Data Index: 5962 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9317. Min Act: -0.0000

Data Index: 864946 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1175694 (The Pile)

Max Activating Token Index: 123