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

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

Neuron 796 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: 1.6651. Min Range: -1.6651

Max Act: 1.6651. Min Act: -0.0000

Data Index: 231079 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6336. Min Act: -0.0000

Data Index: 848956 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.5528. Min Act: -0.0000

Data Index: 1281601 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.3867. Min Act: -0.0000

Data Index: 127979 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.3487. Min Act: -0.0000

Data Index: 750411 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.3115. Min Act: -0.0000

Data Index: 1083363 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.2457. Min Act: -0.0000

Data Index: 261620 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1231563 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.0786. Min Act: -0.0000

Data Index: 388028 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.2208. Min Act: -0.0000

Data Index: 365707 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.2033. Min Act: -0.0000

Data Index: 910389 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.1656. Min Act: -0.0000

Data Index: 934151 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 1.6651. Min Range: -1.6651

Max Act: 0.9966. Min Act: -0.0000

Data Index: 164488 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.1820. Min Act: -0.0000

Data Index: 46511 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.2479. Min Act: -0.0000

Data Index: 413146 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 1.6651. Min Range: -1.6651

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1344654 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.0797. Min Act: -0.0000

Data Index: 556571 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.0317. Min Act: -0.0000

Data Index: 42137 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1303630 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1066896 (C4 (Web Text))

Max Activating Token Index: 34