Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 647 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2428. Min Act: -0.0001

Data Index: 1219095 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2436. Min Act: -0.0001

Data Index: 692605 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2292. Min Act: -0.0001

Data Index: 984006 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2198. Min Act: -0.0001

Data Index: 382963 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2098. Min Act: -0.0001

Data Index: 209006 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1964. Min Act: -0.0001

Data Index: 264409 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1924. Min Act: -0.0001

Data Index: 4730 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1900. Min Act: -0.0001

Data Index: 435716 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1896. Min Act: -0.0001

Data Index: 334800 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1828. Min Act: -0.0001

Data Index: 444298 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1954. Min Act: -0.0001

Data Index: 396285 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1302949 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1947. Min Act: -0.0001

Data Index: 236870 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1930. Min Act: -0.0001

Data Index: 940495 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1253725 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1172834 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1741. Min Act: -0.0001

Data Index: 711860 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1824. Min Act: -0.0001

Data Index: 210625 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1789. Min Act: -0.0001

Data Index: 1268740 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1322976 (C4 (Web Text))

Max Activating Token Index: 135