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

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

Neuron 2531 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0716. Min Act: -0.0001

Data Index: 900245 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1346934 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0512. Min Act: -0.0001

Data Index: 967226 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0493. Min Act: -0.0001

Data Index: 1348731 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0445. Min Act: -0.0001

Data Index: 158098 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0391. Min Act: -0.0001

Data Index: 287914 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0457. Min Act: -0.0001

Data Index: 22637 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0438. Min Act: -0.0001

Data Index: 587062 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0426. Min Act: -0.0001

Data Index: 781126 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0421. Min Act: -0.0001

Data Index: 501014 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0420. Min Act: -0.0001

Data Index: 289292 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0424. Min Act: -0.0001

Data Index: 440550 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0402. Min Act: -0.0001

Data Index: 506471 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0375. Min Act: -0.0001

Data Index: 709418 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0416. Min Act: -0.0001

Data Index: 296166 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1300743 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0417. Min Act: -0.0001

Data Index: 871414 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1284348 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0416. Min Act: -0.0001

Data Index: 952629 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0381. Min Act: -0.0001

Data Index: 601260 (C4 (Web Text))

Max Activating Token Index: 729