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

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

Neuron 1985 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2671. Min Act: 0.0000

Data Index: 1162819 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2299. Min Act: -0.0000

Data Index: 827850 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2616. Min Act: 0.0000

Data Index: 661246 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2559. Min Act: -0.0000

Data Index: 319441 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2379. Min Act: -0.0000

Data Index: 68340 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2339. Min Act: -0.0000

Data Index: 140099 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2323. Min Act: -0.0000

Data Index: 712491 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1266438 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2337. Min Act: -0.0000

Data Index: 144726 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2469. Min Act: -0.0000

Data Index: 708305 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2338. Min Act: -0.0000

Data Index: 40163 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1124061 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2257. Min Act: -0.0000

Data Index: 785965 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2240. Min Act: -0.0000

Data Index: 967628 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.1979. Min Act: -0.0000

Data Index: 510928 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2252. Min Act: -0.0000

Data Index: 283435 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2171. Min Act: -0.0000

Data Index: 841238 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1125712 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1347081 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1321247 (C4 (Web Text))

Max Activating Token Index: 392