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

Dataset: The Pile

Neuron 1077 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1707550 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0346. Min Act: -0.0000

Data Index: 306980 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0481. Min Act: 0.0000

Data Index: 82856 (The Pile)

Max Activating Token Index: 975

Text #3

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0075. Min Act: -0.0000

Data Index: 139921 (The Pile)

Max Activating Token Index: 244

Text #4

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9619. Min Act: -0.0000

Data Index: 1364466 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9513. Min Act: -0.0000

Data Index: 15528 (The Pile)

Max Activating Token Index: 72

Text #6

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9765. Min Act: -0.0000

Data Index: 766888 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1893841 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1949567 (The Pile)

Max Activating Token Index: 732

Text #9

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1255678 (The Pile)

Max Activating Token Index: 597

Text #10

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1554159 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9740. Min Act: -0.0000

Data Index: 443749 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9422. Min Act: -0.0000

Data Index: 538102 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9907. Min Act: 0.0000

Data Index: 941466 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9285. Min Act: -0.0000

Data Index: 980623 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8309. Min Act: -0.0000

Data Index: 48644 (The Pile)

Max Activating Token Index: 377

Text #16

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1846290 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8210. Min Act: -0.0000

Data Index: 812499 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1182301 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1892233 (The Pile)

Max Activating Token Index: 51