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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4056 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8915. Min Act: -0.0000

Data Index: 1136847 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7606. Min Act: -0.0000

Data Index: 1324127 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6652. Min Act: -0.0000

Data Index: 952718 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6581. Min Act: -0.0000

Data Index: 679984 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1009433 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6092. Min Act: -0.0000

Data Index: 753253 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5934. Min Act: -0.0000

Data Index: 954443 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5526. Min Act: -0.0000

Data Index: 943676 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5837. Min Act: -0.0000

Data Index: 715749 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1108071 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5722. Min Act: -0.0000

Data Index: 230982 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1042972 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5533. Min Act: -0.0000

Data Index: 296042 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1266919 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1030393 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.4977. Min Act: -0.0000

Data Index: 151974 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1060128 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5390. Min Act: -0.0000

Data Index: 565851 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5307. Min Act: -0.0001

Data Index: 1201670 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.4868. Min Act: -0.0000

Data Index: 202597 (C4 (Web Text))

Max Activating Token Index: 566