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

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

Neuron 3966 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.5706. Min Act: -0.0000

Data Index: 293510 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.3091. Min Act: -0.0000

Data Index: 826953 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.3181. Min Act: -0.0000

Data Index: 36151 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.3649. Min Act: -0.0000

Data Index: 878453 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1644. Min Act: -0.0000

Data Index: 468850 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1707. Min Act: -0.0000

Data Index: 22714 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.2063. Min Act: -0.0000

Data Index: 1049635 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.2038. Min Act: -0.0000

Data Index: 485055 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1698. Min Act: -0.0000

Data Index: 99608 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1675. Min Act: -0.0000

Data Index: 52939 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1152. Min Act: -0.0000

Data Index: 212109 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1724. Min Act: -0.0000

Data Index: 837415 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1093. Min Act: -0.0000

Data Index: 272945 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1572. Min Act: -0.0000

Data Index: 771431 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1066. Min Act: -0.0000

Data Index: 1216375 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1576. Min Act: -0.0001

Data Index: 1386611 (Python Code)

Max Activating Token Index: 884

Text #16

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1325. Min Act: -0.0000

Data Index: 1272921 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1176. Min Act: -0.0000

Data Index: 774790 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.1163. Min Act: -0.0000

Data Index: 104557 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 2.5706. Min Range: -2.5706

Max Act: 2.0673. Min Act: -0.0000

Data Index: 977329 (C4 (Web Text))

Max Activating Token Index: 681