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

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

Neuron 4874 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1342774 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1005332 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1167146 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3474. Min Act: -0.0000

Data Index: 199486 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2918. Min Act: -0.0000

Data Index: 414909 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2761. Min Act: -0.0000

Data Index: 586993 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1178684 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1311642 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2582. Min Act: -0.0000

Data Index: 492972 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2654. Min Act: -0.0000

Data Index: 979879 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2516. Min Act: -0.0000

Data Index: 58532 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2855. Min Act: -0.0000

Data Index: 766953 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1255827 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2442. Min Act: -0.0000

Data Index: 968674 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1240175 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2522. Min Act: -0.0000

Data Index: 814050 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2374. Min Act: -0.0000

Data Index: 263459 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2376. Min Act: -0.0000

Data Index: 776136 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2448. Min Act: -0.0000

Data Index: 655711 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2436. Min Act: -0.0000

Data Index: 785696 (C4 (Web Text))

Max Activating Token Index: 420