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

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

Neuron 233 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2671. Min Act: -0.0003

Data Index: 703809 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2082. Min Act: -0.0003

Data Index: 1016745 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1675. Min Act: -0.0003

Data Index: 1221082 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1733. Min Act: -0.0002

Data Index: 445568 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1709. Min Act: -0.0003

Data Index: 491664 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1675. Min Act: -0.0002

Data Index: 930609 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1745. Min Act: -0.0002

Data Index: 1208598 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2038. Min Act: -0.0002

Data Index: 434105 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1922. Min Act: -0.0002

Data Index: 973416 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1955. Min Act: -0.0002

Data Index: 215741 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1616. Min Act: -0.0002

Data Index: 549915 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1575. Min Act: -0.0002

Data Index: 502201 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1843. Min Act: -0.0002

Data Index: 855162 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1620. Min Act: -0.0002

Data Index: 1297528 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1501. Min Act: -0.0002

Data Index: 86498 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1587. Min Act: -0.0002

Data Index: 418607 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1529. Min Act: -0.0003

Data Index: 619803 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1452. Min Act: -0.0002

Data Index: 504435 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1534. Min Act: -0.0002

Data Index: 416847 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1646. Min Act: -0.0002

Data Index: 1153039 (C4 (Web Text))

Max Activating Token Index: 212