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

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

Neuron 3257 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3930. Min Act: -0.0000

Data Index: 279984 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3671. Min Act: -0.0000

Data Index: 749011 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3332. Min Act: -0.0001

Data Index: 548433 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3100. Min Act: -0.0000

Data Index: 675870 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3010. Min Act: -0.0001

Data Index: 1296057 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1221495 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2748. Min Act: -0.0001

Data Index: 171891 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1024555 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2775. Min Act: -0.0001

Data Index: 197430 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2734. Min Act: -0.0001

Data Index: 513333 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2646. Min Act: -0.0001

Data Index: 1241585 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2705. Min Act: -0.0001

Data Index: 72294 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1195889 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2582. Min Act: -0.0001

Data Index: 522378 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2654. Min Act: -0.0000

Data Index: 333092 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2627. Min Act: -0.0000

Data Index: 591558 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2554. Min Act: -0.0000

Data Index: 111693 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2620. Min Act: -0.0000

Data Index: 273968 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2608. Min Act: -0.0001

Data Index: 996855 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2603. Min Act: -0.0001

Data Index: 54892 (C4 (Web Text))

Max Activating Token Index: 788