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

Dataset: The Pile

Neuron 1393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.7568. Min Act: -0.0000

Data Index: 1473888 (The Pile)

Max Activating Token Index: 778

Text #1

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.6716. Min Act: -0.0000

Data Index: 1848963 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.6444. Min Act: -0.0000

Data Index: 719610 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.6243. Min Act: -0.0000

Data Index: 1215318 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4070. Min Act: -0.0000

Data Index: 157391 (The Pile)

Max Activating Token Index: 926

Text #5

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.6623. Min Act: -0.0000

Data Index: 1534354 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.5600. Min Act: -0.0000

Data Index: 1935679 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.5676. Min Act: -0.0000

Data Index: 1920229 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4664. Min Act: -0.0000

Data Index: 1065054 (The Pile)

Max Activating Token Index: 305

Text #9

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4232. Min Act: -0.0000

Data Index: 246917 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4044. Min Act: -0.0000

Data Index: 1671050 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4917. Min Act: -0.0000

Data Index: 1731000 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1866178 (The Pile)

Max Activating Token Index: 921

Text #13

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.3666. Min Act: -0.0000

Data Index: 95995 (The Pile)

Max Activating Token Index: 100

Text #14

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4399. Min Act: -0.0000

Data Index: 427241 (The Pile)

Max Activating Token Index: 593

Text #15

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4459. Min Act: -0.0000

Data Index: 395850 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.3600. Min Act: -0.0000

Data Index: 1284235 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1975790 (The Pile)

Max Activating Token Index: 908

Text #18

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4881. Min Act: -0.0000

Data Index: 1187551 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.3882. Min Act: -0.0000

Data Index: 970457 (The Pile)

Max Activating Token Index: 799