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

Dataset: The Pile

Neuron 4093 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.9431. Min Act: 0.0000

Data Index: 443448 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1061186 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.7450. Min Act: -0.0000

Data Index: 1859692 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.7107. Min Act: -0.0000

Data Index: 1443641 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6650. Min Act: -0.0000

Data Index: 748708 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.7046. Min Act: -0.0000

Data Index: 977886 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1698803 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1718863 (The Pile)

Max Activating Token Index: 907

Text #8

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.7162. Min Act: -0.0000

Data Index: 4182 (The Pile)

Max Activating Token Index: 913

Text #9

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6829. Min Act: -0.0000

Data Index: 367532 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1651550 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1622993 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6485. Min Act: -0.0000

Data Index: 111196 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6647. Min Act: -0.0000

Data Index: 794219 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6595. Min Act: -0.0000

Data Index: 814175 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1154607 (The Pile)

Max Activating Token Index: 327

Text #16

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1424070 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6388. Min Act: -0.0000

Data Index: 800261 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1972500 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6282. Min Act: -0.0000

Data Index: 786277 (The Pile)

Max Activating Token Index: 546