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

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

Neuron 1867 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1781. Min Act: -0.0001

Data Index: 668976 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1575. Min Act: -0.0001

Data Index: 911465 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1549. Min Act: -0.0001

Data Index: 991262 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1546. Min Act: 0.0000

Data Index: 383070 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1396. Min Act: -0.0001

Data Index: 241494 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1395. Min Act: -0.0001

Data Index: 642063 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1081273 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1376. Min Act: -0.0001

Data Index: 36085 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1303. Min Act: -0.0001

Data Index: 48554 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1009388 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1284. Min Act: -0.0001

Data Index: 778353 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1281. Min Act: -0.0001

Data Index: 938247 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1264. Min Act: -0.0001

Data Index: 823721 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1243. Min Act: -0.0001

Data Index: 997492 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1230. Min Act: -0.0001

Data Index: 334919 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1257. Min Act: -0.0001

Data Index: 984263 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1148019 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1089791 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1135. Min Act: -0.0001

Data Index: 395462 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1128291 (C4 (Web Text))

Max Activating Token Index: 897