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

Dataset: The Pile

Neuron 1418 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: 3.0662. Min Range: -3.0662

Max Act: 3.0662. Min Act: -0.0000

Data Index: 1510211 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.2265. Min Act: -0.0000

Data Index: 547489 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.1663. Min Act: -0.0000

Data Index: 192899 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.1696. Min Act: -0.0000

Data Index: 543410 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.0444. Min Act: -0.0000

Data Index: 975817 (The Pile)

Max Activating Token Index: 35

Text #5

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.0384. Min Act: -0.0000

Data Index: 599751 (The Pile)

Max Activating Token Index: 392

Text #6

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.9933. Min Act: -0.0000

Data Index: 987876 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.9816. Min Act: -0.0000

Data Index: 745504 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.7938. Min Act: -0.0000

Data Index: 242096 (The Pile)

Max Activating Token Index: 341

Text #9

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.9078. Min Act: -0.0000

Data Index: 1026861 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.8464. Min Act: -0.0000

Data Index: 389717 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.9405. Min Act: -0.0000

Data Index: 481697 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.8298. Min Act: -0.0000

Data Index: 77266 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.8106. Min Act: -0.0000

Data Index: 120059 (The Pile)

Max Activating Token Index: 494

Text #14

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.7064. Min Act: -0.0000

Data Index: 770767 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1171844 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.8997. Min Act: -0.0000

Data Index: 1518613 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.7708. Min Act: -0.0000

Data Index: 1498931 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.7645. Min Act: -0.0000

Data Index: 28504 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 3.0662. Min Range: -3.0662

Max Act: 1.8309. Min Act: -0.0000

Data Index: 45856 (The Pile)

Max Activating Token Index: 138