Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 200 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.5721. Min Act: -0.0003

Data Index: 734335 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.5155. Min Act: -0.0003

Data Index: 1034104 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3732. Min Act: -0.0003

Data Index: 967233 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3951. Min Act: -0.0003

Data Index: 974697 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3551. Min Act: -0.0003

Data Index: 1084265 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3202. Min Act: -0.0003

Data Index: 112852 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3406. Min Act: -0.0003

Data Index: 1146692 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.2593. Min Act: -0.0003

Data Index: 707365 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4467. Min Act: -0.0003

Data Index: 1089603 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3386. Min Act: -0.0003

Data Index: 48366 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3463. Min Act: -0.0003

Data Index: 560161 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3532. Min Act: -0.0003

Data Index: 840091 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3212. Min Act: -0.0003

Data Index: 1248087 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3357. Min Act: -0.0003

Data Index: 1279099 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.2933. Min Act: -0.0003

Data Index: 41445 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3455. Min Act: -0.0003

Data Index: 1199729 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.2737. Min Act: -0.0003

Data Index: 1236822 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3393. Min Act: -0.0003

Data Index: 720945 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3621. Min Act: -0.0003

Data Index: 38095 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.3871. Min Act: -0.0003

Data Index: 955488 (C4 (Web Text))

Max Activating Token Index: 509