Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2715 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1888. Min Act: -0.0001

Data Index: 464676 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1953. Min Act: -0.0001

Data Index: 45133 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1788. Min Act: -0.0001

Data Index: 214815 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1918. Min Act: -0.0001

Data Index: 510125 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1773. Min Act: -0.0001

Data Index: 875151 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1652. Min Act: -0.0001

Data Index: 729853 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1693. Min Act: -0.0001

Data Index: 977914 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1630. Min Act: -0.0001

Data Index: 516402 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1254821 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1673. Min Act: -0.0001

Data Index: 272564 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1657. Min Act: -0.0001

Data Index: 306484 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1351099 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1573. Min Act: -0.0001

Data Index: 266592 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1627. Min Act: -0.0001

Data Index: 219905 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1637. Min Act: -0.0001

Data Index: 17776 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1206108 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1549. Min Act: -0.0001

Data Index: 139104 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1569. Min Act: -0.0001

Data Index: 537191 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1531. Min Act: -0.0001

Data Index: 750768 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1356386 (C4 (Web Text))

Max Activating Token Index: 973