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

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

Neuron 5836 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1132685 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1018676 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7485. Min Act: -0.0000

Data Index: 938442 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7658. Min Act: -0.0000

Data Index: 795692 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7265. Min Act: -0.0000

Data Index: 725985 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1246299 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1132232 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6812. Min Act: -0.0000

Data Index: 878653 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6340. Min Act: -0.0000

Data Index: 981338 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6739. Min Act: -0.0000

Data Index: 915753 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6962. Min Act: -0.0000

Data Index: 186519 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6592. Min Act: -0.0000

Data Index: 183656 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1443310 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.5821. Min Act: -0.0000

Data Index: 425949 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6301. Min Act: -0.0000

Data Index: 491699 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1240811 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1647491 (Python Code)

Max Activating Token Index: 604

Text #17

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.5799. Min Act: -0.0000

Data Index: 840345 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.5547. Min Act: -0.0000

Data Index: 605329 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1609106 (Python Code)

Max Activating Token Index: 474