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

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

Neuron 553 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1307738 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1111755 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1218017 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1468. Min Act: -0.0001

Data Index: 19102 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1417. Min Act: -0.0001

Data Index: 803706 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1391. Min Act: -0.0000

Data Index: 384851 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1277. Min Act: -0.0001

Data Index: 742973 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1294. Min Act: -0.0001

Data Index: 384860 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1239. Min Act: -0.0001

Data Index: 23611 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1274. Min Act: -0.0001

Data Index: 16273 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1227. Min Act: -0.0001

Data Index: 844337 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1221. Min Act: -0.0001

Data Index: 454900 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1204. Min Act: -0.0001

Data Index: 945248 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1303487 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1150. Min Act: -0.0000

Data Index: 791746 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1227. Min Act: -0.0000

Data Index: 783203 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1172. Min Act: -0.0000

Data Index: 334582 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1050491 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1201. Min Act: -0.0000

Data Index: 220760 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1157. Min Act: -0.0000

Data Index: 468903 (C4 (Web Text))

Max Activating Token Index: 45