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

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

Neuron 337 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.2466. Min Act: -0.0001

Data Index: 61694 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.2646. Min Act: -0.0002

Data Index: 111367 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.2256. Min Act: -0.0001

Data Index: 1109336 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.2037. Min Act: -0.0001

Data Index: 309276 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.1046. Min Act: -0.0001

Data Index: 520972 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.1326. Min Act: -0.0001

Data Index: 389554 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.0663. Min Act: -0.0001

Data Index: 78720 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.1148. Min Act: -0.0001

Data Index: 156111 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.0431. Min Act: -0.0001

Data Index: 170154 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.0528. Min Act: -0.0001

Data Index: 748676 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 1.2646. Min Range: -1.2646

Max Act: 0.9871. Min Act: -0.0002

Data Index: 318591 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.0183. Min Act: -0.0001

Data Index: 153148 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.0679. Min Act: -0.0001

Data Index: 271569 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.0306. Min Act: -0.0002

Data Index: 46156 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.0248. Min Act: -0.0002

Data Index: 587905 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 1.2646. Min Range: -1.2646

Max Act: 0.9984. Min Act: -0.0001

Data Index: 984673 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 1.2646. Min Range: -1.2646

Max Act: 0.9597. Min Act: -0.0002

Data Index: 1316092 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 1.2646. Min Range: -1.2646

Max Act: 0.9523. Min Act: -0.0002

Data Index: 988690 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 1.2646. Min Range: -1.2646

Max Act: 0.9636. Min Act: -0.0002

Data Index: 579472 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.2646. Min Range: -1.2646

Max Act: 1.0116. Min Act: -0.0002

Data Index: 790434 (C4 (Web Text))

Max Activating Token Index: 789