Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3519 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.8962. Min Act: -0.0000

Data Index: 897931 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.6977. Min Act: -0.0000

Data Index: 529929 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.5389. Min Act: -0.0000

Data Index: 993492 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.6213. Min Act: -0.0000

Data Index: 285363 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.5200. Min Act: -0.0000

Data Index: 1148978 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.2794. Min Act: -0.0000

Data Index: 79864 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.3221. Min Act: -0.0000

Data Index: 721585 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.3267. Min Act: -0.0000

Data Index: 786349 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1298109 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1173846 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.1449. Min Act: -0.0000

Data Index: 1212544 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.2087. Min Act: -0.0000

Data Index: 780874 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.1260. Min Act: -0.0000

Data Index: 451047 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1270202 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.0895. Min Act: -0.0000

Data Index: 707030 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.0548. Min Act: -0.0000

Data Index: 673938 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 1.8962. Min Range: -1.8962

Max Act: 0.9597. Min Act: -0.0000

Data Index: 312011 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.0046. Min Act: -0.0000

Data Index: 816568 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.1006. Min Act: -0.0000

Data Index: 954263 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1025462 (C4 (Web Text))

Max Activating Token Index: 311