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

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

Neuron 2771 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: 3.4759. Min Range: -3.4759

Max Act: 3.4759. Min Act: -0.0001

Data Index: 520491 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 3.4759. Min Range: -3.4759

Max Act: 3.4438. Min Act: -0.0001

Data Index: 795772 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 3.4759. Min Range: -3.4759

Max Act: 3.1545. Min Act: -0.0001

Data Index: 176268 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.9429. Min Act: -0.0001

Data Index: 628681 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.8082. Min Act: -0.0001

Data Index: 1253388 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.9399. Min Act: -0.0001

Data Index: 172306 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.9008. Min Act: -0.0001

Data Index: 671756 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.8081. Min Act: -0.0001

Data Index: 1337552 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.5400. Min Act: -0.0000

Data Index: 480494 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.7716. Min Act: -0.0001

Data Index: 13775 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.6395. Min Act: -0.0000

Data Index: 90245 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.8865. Min Act: -0.0001

Data Index: 612915 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.4784. Min Act: -0.0000

Data Index: 681207 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.6121. Min Act: -0.0001

Data Index: 76391 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.7359. Min Act: -0.0001

Data Index: 726743 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.8444. Min Act: -0.0001

Data Index: 1233153 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.6701. Min Act: -0.0001

Data Index: 235401 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.7897. Min Act: -0.0001

Data Index: 912491 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.5120. Min Act: -0.0001

Data Index: 873710 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 3.4759. Min Range: -3.4759

Max Act: 2.8867. Min Act: -0.0001

Data Index: 1127597 (C4 (Web Text))

Max Activating Token Index: 824