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

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

Neuron 5478 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2654. Min Act: -0.0000

Data Index: 952236 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2623. Min Act: -0.0000

Data Index: 729320 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2701. Min Act: -0.0000

Data Index: 227058 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2561. Min Act: -0.0000

Data Index: 925046 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2690. Min Act: -0.0000

Data Index: 204401 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2523. Min Act: -0.0000

Data Index: 887370 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2381. Min Act: -0.0000

Data Index: 55570 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2310. Min Act: -0.0000

Data Index: 270777 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1241196 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1306174 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2493. Min Act: -0.0000

Data Index: 95470 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2499. Min Act: -0.0000

Data Index: 939999 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2184. Min Act: -0.0000

Data Index: 68545 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1038204 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2115. Min Act: -0.0000

Data Index: 98423 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2295. Min Act: -0.0000

Data Index: 915470 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2260. Min Act: -0.0000

Data Index: 670060 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2352. Min Act: -0.0000

Data Index: 466514 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2347. Min Act: -0.0000

Data Index: 337759 (C4 (Web Text))

Max Activating Token Index: 840