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

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

Neuron 1100 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.2463. Min Act: -0.0001

Data Index: 687436 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.2458. Min Act: -0.0001

Data Index: 342377 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.2108. Min Act: -0.0001

Data Index: 962603 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.2055. Min Act: -0.0001

Data Index: 194209 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.2111. Min Act: -0.0001

Data Index: 29593 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.2010. Min Act: -0.0001

Data Index: 1134311 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1095053 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.2031. Min Act: -0.0001

Data Index: 554859 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1828. Min Act: -0.0001

Data Index: 1104231 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1931. Min Act: -0.0001

Data Index: 616884 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1852. Min Act: -0.0001

Data Index: 1175304 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1973. Min Act: -0.0001

Data Index: 1355781 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1836. Min Act: -0.0000

Data Index: 682511 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1704. Min Act: -0.0001

Data Index: 1168077 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1818. Min Act: -0.0001

Data Index: 654238 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1774. Min Act: -0.0001

Data Index: 305270 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1050722 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1785. Min Act: -0.0001

Data Index: 882289 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1682. Min Act: -0.0001

Data Index: 701310 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.2463. Min Range: -0.2463

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1350567 (C4 (Web Text))

Max Activating Token Index: 377