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

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

Neuron 1800 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: 0.1890. Min Range: -0.1890

Max Act: 0.1686. Min Act: -0.0001

Data Index: 263101 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1852. Min Act: -0.0001

Data Index: 1231998 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1822. Min Act: -0.0001

Data Index: 511035 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1755. Min Act: -0.0001

Data Index: 422244 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1696. Min Act: -0.0001

Data Index: 376702 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1804. Min Act: -0.0001

Data Index: 1170638 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1890. Min Act: -0.0001

Data Index: 573044 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1646. Min Act: -0.0001

Data Index: 227942 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1698. Min Act: -0.0001

Data Index: 182168 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1758. Min Act: -0.0001

Data Index: 1001455 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1688. Min Act: -0.0001

Data Index: 986641 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1845. Min Act: -0.0001

Data Index: 1043301 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1117811 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1636. Min Act: -0.0001

Data Index: 750433 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1526. Min Act: -0.0001

Data Index: 978265 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1467. Min Act: -0.0001

Data Index: 867372 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1353841 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1494. Min Act: -0.0000

Data Index: 48570 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1097204 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1302023 (C4 (Web Text))

Max Activating Token Index: 668