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

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

Neuron 2019 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1585. Min Act: -0.0001

Data Index: 761357 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1594. Min Act: -0.0000

Data Index: 459678 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1638. Min Act: -0.0000

Data Index: 386132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1031959 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1490. Min Act: -0.0000

Data Index: 791119 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1264. Min Act: -0.0001

Data Index: 452130 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1446. Min Act: -0.0001

Data Index: 171368 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1386. Min Act: -0.0001

Data Index: 499554 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1226. Min Act: -0.0000

Data Index: 268787 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1241. Min Act: -0.0001

Data Index: 109483 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1238350 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1216. Min Act: -0.0000

Data Index: 406570 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1343. Min Act: -0.0000

Data Index: 349006 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1268. Min Act: -0.0000

Data Index: 208979 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1255. Min Act: -0.0001

Data Index: 374410 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1247232 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1267. Min Act: -0.0000

Data Index: 759083 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1145. Min Act: -0.0001

Data Index: 104628 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1146. Min Act: -0.0001

Data Index: 559668 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.1638. Min Range: -0.1638

Max Act: 0.1135. Min Act: -0.0001

Data Index: 772983 (C4 (Web Text))

Max Activating Token Index: 225