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

Dataset: The Pile

Neuron 1027 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.4444. Min Act: -0.0001

Data Index: 59336 (The Pile)

Max Activating Token Index: 820

Text #1

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1262332 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0622. Min Act: -0.0001

Data Index: 1905212 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0601. Min Act: -0.0000

Data Index: 116311 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0964. Min Act: -0.0001

Data Index: 1054596 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0712. Min Act: -0.0000

Data Index: 540158 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0635. Min Act: -0.0000

Data Index: 751663 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0047. Min Act: -0.0001

Data Index: 769198 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1441516 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1620670 (The Pile)

Max Activating Token Index: 998

Text #10

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.9707. Min Act: -0.0000

Data Index: 627015 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8947. Min Act: -0.0001

Data Index: 1887451 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8213. Min Act: -0.0000

Data Index: 581373 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.9253. Min Act: -0.0000

Data Index: 781034 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1031524 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.9064. Min Act: -0.0000

Data Index: 745797 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.7765. Min Act: -0.0000

Data Index: 863107 (The Pile)

Max Activating Token Index: 633

Text #17

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8974. Min Act: -0.0000

Data Index: 278546 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8965. Min Act: -0.0001

Data Index: 1169886 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1075664 (The Pile)

Max Activating Token Index: 250