Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2235 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1452. Min Act: -0.0001

Data Index: 42184 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1650. Min Act: -0.0001

Data Index: 160025 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1531. Min Act: -0.0001

Data Index: 703458 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1659. Min Act: -0.0001

Data Index: 738559 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1537. Min Act: -0.0001

Data Index: 307412 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1029923 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1293882 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1502. Min Act: -0.0001

Data Index: 904973 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1327693 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1304. Min Act: -0.0001

Data Index: 959980 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1283. Min Act: -0.0001

Data Index: 960225 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1045557 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1215. Min Act: -0.0001

Data Index: 667798 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1236. Min Act: -0.0001

Data Index: 142123 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1259. Min Act: -0.0001

Data Index: 914240 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1277. Min Act: -0.0001

Data Index: 6702 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1117. Min Act: -0.0000

Data Index: 587205 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1290. Min Act: -0.0001

Data Index: 75712 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1330167 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1223683 (C4 (Web Text))

Max Activating Token Index: 197