Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1119 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0301. Min Act: -0.0001

Data Index: 531514 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0283. Min Act: -0.0001

Data Index: 182605 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0273. Min Act: -0.0001

Data Index: 114826 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1287243 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0266. Min Act: -0.0001

Data Index: 666690 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1244602 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0259. Min Act: -0.0001

Data Index: 419370 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0265. Min Act: -0.0001

Data Index: 367278 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1201803 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0251. Min Act: -0.0001

Data Index: 563285 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1313283 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1129745 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1017365 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0287. Min Act: -0.0001

Data Index: 79052 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0255. Min Act: -0.0001

Data Index: 173155 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0242. Min Act: -0.0001

Data Index: 923076 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0261. Min Act: -0.0001

Data Index: 297520 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0246. Min Act: -0.0001

Data Index: 605350 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0260. Min Act: -0.0001

Data Index: 935772 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0222. Min Act: -0.0001

Data Index: 630522 (C4 (Web Text))

Max Activating Token Index: 600