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

Dataset: The Pile

Neuron 1816 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: 4.3480. Min Range: -4.3480

Max Act: 4.3480. Min Act: -0.0000

Data Index: 465252 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.7526. Min Act: -0.0000

Data Index: 1341242 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.8609. Min Act: -0.0000

Data Index: 39732 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.8454. Min Act: -0.0000

Data Index: 1253769 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.8457. Min Act: -0.0000

Data Index: 826642 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.6628. Min Act: -0.0000

Data Index: 809751 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.6138. Min Act: -0.0000

Data Index: 623828 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.9191. Min Act: -0.0000

Data Index: 1461754 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.7559. Min Act: -0.0000

Data Index: 902998 (The Pile)

Max Activating Token Index: 417

Text #9

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.5578. Min Act: -0.0000

Data Index: 181719 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.7048. Min Act: -0.0000

Data Index: 1820151 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.6284. Min Act: -0.0000

Data Index: 221570 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.7951. Min Act: -0.0000

Data Index: 1037611 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.4950. Min Act: -0.0000

Data Index: 260181 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.7859. Min Act: -0.0000

Data Index: 1262973 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.7559. Min Act: -0.0000

Data Index: 1393688 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.5866. Min Act: -0.0000

Data Index: 984804 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.7417. Min Act: -0.0000

Data Index: 966356 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.1472. Min Act: -0.0000

Data Index: 81802 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.7183. Min Act: -0.0000

Data Index: 612192 (The Pile)

Max Activating Token Index: 523