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

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

Neuron 3610 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: 0.1436. Min Range: -0.1436

Max Act: 0.1361. Min Act: -0.0001

Data Index: 588618 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1436. Min Act: -0.0002

Data Index: 153140 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1373. Min Act: -0.0002

Data Index: 714306 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1357. Min Act: -0.0001

Data Index: 79100 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1272. Min Act: -0.0001

Data Index: 170490 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1261. Min Act: -0.0002

Data Index: 1189239 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1344. Min Act: -0.0001

Data Index: 537642 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1343. Min Act: -0.0001

Data Index: 993603 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1317. Min Act: -0.0002

Data Index: 1253008 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1213743 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1070274 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1213. Min Act: -0.0002

Data Index: 95754 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1240. Min Act: -0.0001

Data Index: 243184 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1097714 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1268. Min Act: -0.0001

Data Index: 359733 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1248. Min Act: -0.0002

Data Index: 1089108 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1260. Min Act: -0.0001

Data Index: 179464 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1224. Min Act: -0.0002

Data Index: 207451 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1186. Min Act: -0.0001

Data Index: 137368 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1222. Min Act: -0.0001

Data Index: 20528 (C4 (Web Text))

Max Activating Token Index: 911