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

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

Neuron 3861 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: 1.0565. Min Range: -1.0565

Max Act: 1.0565. Min Act: -0.0001

Data Index: 1127234 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7917. Min Act: -0.0001

Data Index: 97225 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.9670. Min Act: -0.0001

Data Index: 424135 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.9334. Min Act: -0.0001

Data Index: 850313 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.5577. Min Act: -0.0001

Data Index: 302909 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7968. Min Act: -0.0001

Data Index: 1295659 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.8206. Min Act: -0.0001

Data Index: 1231888 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7666. Min Act: -0.0001

Data Index: 591051 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7890. Min Act: -0.0001

Data Index: 1169901 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7742. Min Act: -0.0001

Data Index: 762131 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7921. Min Act: -0.0001

Data Index: 42657 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.8313. Min Act: -0.0001

Data Index: 782895 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7447. Min Act: -0.0001

Data Index: 1318228 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.8557. Min Act: -0.0001

Data Index: 321978 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.6607. Min Act: -0.0001

Data Index: 899103 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7244. Min Act: -0.0001

Data Index: 666802 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7241. Min Act: -0.0001

Data Index: 994698 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7445. Min Act: -0.0001

Data Index: 521544 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.6917. Min Act: -0.0001

Data Index: 425248 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.0565. Min Range: -1.0565

Max Act: 0.7110. Min Act: -0.0001

Data Index: 782207 (C4 (Web Text))

Max Activating Token Index: 575