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

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

Neuron 3626 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1417. Min Act: -0.0001

Data Index: 953362 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1385. Min Act: -0.0001

Data Index: 189278 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1434. Min Act: -0.0001

Data Index: 521415 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1477. Min Act: -0.0001

Data Index: 208773 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1414. Min Act: -0.0001

Data Index: 186032 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1464. Min Act: -0.0002

Data Index: 1299501 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1290. Min Act: -0.0001

Data Index: 142883 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1187713 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1280. Min Act: -0.0001

Data Index: 390881 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1295. Min Act: -0.0001

Data Index: 119686 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1141538 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1050450 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1098549 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1230167 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1184. Min Act: -0.0001

Data Index: 515607 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1176175 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1217. Min Act: -0.0001

Data Index: 590375 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1014030 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1198. Min Act: -0.0002

Data Index: 563983 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1186. Min Act: -0.0001

Data Index: 176509 (C4 (Web Text))

Max Activating Token Index: 44