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

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

Neuron 794 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1503. Min Act: -0.0001

Data Index: 532014 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1320. Min Act: -0.0001

Data Index: 347766 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1385. Min Act: -0.0001

Data Index: 262190 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1374. Min Act: -0.0001

Data Index: 767719 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1368. Min Act: -0.0001

Data Index: 202816 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1069552 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1354603 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1141. Min Act: -0.0001

Data Index: 26548 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1160. Min Act: -0.0001

Data Index: 673659 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1154656 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1128570 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1072. Min Act: -0.0001

Data Index: 688973 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1003. Min Act: -0.0001

Data Index: 347985 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1329902 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1344761 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.0940. Min Act: -0.0001

Data Index: 498423 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.0933. Min Act: -0.0001

Data Index: 258401 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.0904. Min Act: -0.0001

Data Index: 307528 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.0960. Min Act: -0.0001

Data Index: 143955 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.0823. Min Act: -0.0001

Data Index: 227479 (C4 (Web Text))

Max Activating Token Index: 656