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

Dataset: The Pile

Neuron 443 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: 1.2773. Min Range: -1.2773

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1768167 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1274223 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0173. Min Act: -0.0000

Data Index: 626198 (The Pile)

Max Activating Token Index: 936

Text #3

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1792955 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1210558 (The Pile)

Max Activating Token Index: 99

Text #5

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9658. Min Act: -0.0000

Data Index: 706250 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1149996 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9682. Min Act: -0.0000

Data Index: 727875 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9529. Min Act: -0.0000

Data Index: 323287 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1571454 (The Pile)

Max Activating Token Index: 766

Text #10

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1170021 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.8991. Min Act: -0.0000

Data Index: 184413 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1687969 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.8612. Min Act: -0.0000

Data Index: 311209 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1591289 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.8767. Min Act: -0.0000

Data Index: 44018 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9043. Min Act: -0.0000

Data Index: 578897 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.8452. Min Act: -0.0000

Data Index: 724665 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9234. Min Act: -0.0000

Data Index: 965745 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.8898. Min Act: -0.0000

Data Index: 487624 (The Pile)

Max Activating Token Index: 301