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

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

Neuron 3045 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7729. Min Act: -0.0001

Data Index: 988859 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6552. Min Act: -0.0001

Data Index: 249981 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6772. Min Act: -0.0001

Data Index: 851918 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6332. Min Act: -0.0001

Data Index: 1316249 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5962. Min Act: -0.0001

Data Index: 41965 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5319. Min Act: -0.0001

Data Index: 1067689 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1170465 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5604. Min Act: -0.0001

Data Index: 222477 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5090. Min Act: -0.0001

Data Index: 673649 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4888. Min Act: -0.0001

Data Index: 918474 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4942. Min Act: -0.0000

Data Index: 556034 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5131. Min Act: -0.0000

Data Index: 195945 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4747. Min Act: -0.0000

Data Index: 32427 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4834. Min Act: -0.0000

Data Index: 360646 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4749. Min Act: -0.0001

Data Index: 1084519 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4984. Min Act: -0.0001

Data Index: 205826 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4992. Min Act: -0.0000

Data Index: 805120 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4328. Min Act: -0.0001

Data Index: 244854 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4367. Min Act: -0.0000

Data Index: 925125 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5114. Min Act: -0.0000

Data Index: 298289 (C4 (Web Text))

Max Activating Token Index: 573