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

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

Neuron 4246 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1531302 (Python Code)

Max Activating Token Index: 998

Text #1

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1692. Min Act: -0.0000

Data Index: 134705 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1657. Min Act: -0.0000

Data Index: 851655 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1534. Min Act: -0.0000

Data Index: 975884 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1437. Min Act: -0.0000

Data Index: 670379 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1320067 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1374. Min Act: -0.0000

Data Index: 378532 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1271. Min Act: -0.0000

Data Index: 601507 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1193289 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1145731 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1535635 (Python Code)

Max Activating Token Index: 968

Text #11

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1147843 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1002932 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1273. Min Act: -0.0000

Data Index: 68864 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1304. Min Act: -0.0000

Data Index: 846203 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1229. Min Act: -0.0000

Data Index: 342848 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1164. Min Act: -0.0000

Data Index: 738428 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1200. Min Act: -0.0000

Data Index: 624019 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1241. Min Act: -0.0000

Data Index: 371443 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1118. Min Act: -0.0000

Data Index: 459749 (C4 (Web Text))

Max Activating Token Index: 909