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

Dataset: The Pile

Neuron 1676 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6537. Min Act: -0.0000

Data Index: 685604 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1956272 (The Pile)

Max Activating Token Index: 434

Text #2

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1538422 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1043357 (The Pile)

Max Activating Token Index: 410

Text #4

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1753415 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1601197 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1543807 (The Pile)

Max Activating Token Index: 360

Text #7

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6841. Min Act: -0.0000

Data Index: 995759 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6637. Min Act: -0.0000

Data Index: 132420 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1218676 (The Pile)

Max Activating Token Index: 331

Text #10

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6791. Min Act: -0.0000

Data Index: 677203 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6576. Min Act: -0.0000

Data Index: 482751 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5840. Min Act: -0.0000

Data Index: 186679 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6687. Min Act: -0.0000

Data Index: 863784 (The Pile)

Max Activating Token Index: 879

Text #14

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6691. Min Act: -0.0000

Data Index: 815443 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6630. Min Act: -0.0000

Data Index: 892350 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6607. Min Act: -0.0000

Data Index: 599092 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1480634 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6606. Min Act: -0.0000

Data Index: 724734 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6851. Min Act: -0.0000

Data Index: 702578 (The Pile)

Max Activating Token Index: 636