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

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

Neuron 4453 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0548. Min Act: -0.0002

Data Index: 972194 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0002

Data Index: 446334 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0584. Min Act: -0.0002

Data Index: 485911 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0577. Min Act: -0.0002

Data Index: 546500 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1244868 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1121007 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0519. Min Act: -0.0002

Data Index: 664429 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0499. Min Act: -0.0002

Data Index: 654862 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0511. Min Act: -0.0002

Data Index: 723753 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0452. Min Act: -0.0002

Data Index: 726961 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1336758 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0460. Min Act: -0.0002

Data Index: 53135 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0416. Min Act: -0.0002

Data Index: 763401 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0460. Min Act: -0.0002

Data Index: 592195 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0480. Min Act: -0.0002

Data Index: 742174 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1260225 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0459. Min Act: -0.0002

Data Index: 269590 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1168361 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0485. Min Act: -0.0002

Data Index: 644691 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0414. Min Act: -0.0002

Data Index: 687660 (C4 (Web Text))

Max Activating Token Index: 119