Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2239 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1318625 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1035335 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1757. Min Act: -0.0001

Data Index: 621425 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1768. Min Act: -0.0001

Data Index: 103764 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1243372 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1664. Min Act: -0.0000

Data Index: 224625 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1580. Min Act: -0.0000

Data Index: 473640 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1570794 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1605. Min Act: -0.0000

Data Index: 286463 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1596. Min Act: -0.0001

Data Index: 113757 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1580. Min Act: -0.0000

Data Index: 973553 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1621. Min Act: -0.0000

Data Index: 175917 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1584. Min Act: -0.0000

Data Index: 40230 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1605. Min Act: -0.0001

Data Index: 440156 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1604. Min Act: -0.0000

Data Index: 45263 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1594. Min Act: -0.0000

Data Index: 249835 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1419609 (Python Code)

Max Activating Token Index: 484

Text #17

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1518. Min Act: -0.0001

Data Index: 96516 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1147565 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1570. Min Act: -0.0000

Data Index: 372119 (C4 (Web Text))

Max Activating Token Index: 498