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

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

Neuron 3704 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.2172. Min Act: -0.0000

Data Index: 146555 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1717. Min Act: -0.0000

Data Index: 436931 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1006596 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1533. Min Act: -0.0000

Data Index: 115845 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1170323 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1175559 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1456. Min Act: -0.0000

Data Index: 385239 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1458. Min Act: -0.0000

Data Index: 879964 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1321. Min Act: -0.0000

Data Index: 221865 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1301. Min Act: -0.0000

Data Index: 361033 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1244. Min Act: -0.0000

Data Index: 233292 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1331. Min Act: -0.0000

Data Index: 576650 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1350. Min Act: -0.0000

Data Index: 764807 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1219. Min Act: -0.0000

Data Index: 29836 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1284. Min Act: -0.0000

Data Index: 682857 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1240. Min Act: -0.0000

Data Index: 395411 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1274. Min Act: -0.0000

Data Index: 744258 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1227. Min Act: -0.0000

Data Index: 753313 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1202. Min Act: -0.0000

Data Index: 129375 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1200. Min Act: -0.0000

Data Index: 255343 (C4 (Web Text))

Max Activating Token Index: 188