Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3378 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8788. Min Range: -2.8788

Max Act: 2.8788. Min Act: -0.0000

Data Index: 781929 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 2.8788. Min Range: -2.8788

Max Act: 2.3332. Min Act: -0.0000

Data Index: 519910 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 2.8788. Min Range: -2.8788

Max Act: 2.2542. Min Act: -0.0000

Data Index: 878794 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 2.8788. Min Range: -2.8788

Max Act: 2.1689. Min Act: -0.0000

Data Index: 1027661 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 2.8788. Min Range: -2.8788

Max Act: 2.0146. Min Act: -0.0000

Data Index: 1040667 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.9912. Min Act: -0.0000

Data Index: 826777 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 2.8788. Min Range: -2.8788

Max Act: 2.0725. Min Act: -0.0000

Data Index: 809523 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.9618. Min Act: -0.0000

Data Index: 334239 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.9597. Min Act: -0.0000

Data Index: 793647 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.6545. Min Act: -0.0000

Data Index: 282723 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.8455. Min Act: -0.0000

Data Index: 563953 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.7445. Min Act: -0.0000

Data Index: 373773 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.7865. Min Act: -0.0000

Data Index: 794678 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.6857. Min Act: -0.0000

Data Index: 1154105 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.7825. Min Act: -0.0000

Data Index: 1068345 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.8674. Min Act: -0.0000

Data Index: 109393 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.6755. Min Act: -0.0000

Data Index: 793338 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.7346. Min Act: -0.0000

Data Index: 569495 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.7168. Min Act: -0.0000

Data Index: 512310 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 2.8788. Min Range: -2.8788

Max Act: 1.6995. Min Act: -0.0000

Data Index: 1357003 (C4 (Web Text))

Max Activating Token Index: 39