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

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

Neuron 999 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1457. Min Act: -0.0002

Data Index: 1186674 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1311. Min Act: -0.0002

Data Index: 193986 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1199. Min Act: -0.0002

Data Index: 701693 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1203. Min Act: -0.0002

Data Index: 145468 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1093144 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1267. Min Act: -0.0002

Data Index: 1284417 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1458. Min Act: -0.0002

Data Index: 739710 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1337. Min Act: -0.0002

Data Index: 1298209 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1275. Min Act: -0.0002

Data Index: 674407 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1268. Min Act: -0.0002

Data Index: 13728 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1364. Min Act: -0.0002

Data Index: 843318 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1159. Min Act: -0.0002

Data Index: 897806 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1188. Min Act: -0.0002

Data Index: 728434 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1285611 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1161. Min Act: -0.0002

Data Index: 511336 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1171. Min Act: -0.0002

Data Index: 566880 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1108473 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1068. Min Act: -0.0002

Data Index: 121312 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1220. Min Act: -0.0002

Data Index: 1061192 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1260. Min Act: -0.0002

Data Index: 190474 (C4 (Web Text))

Max Activating Token Index: 685