Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.6342. Min Act: -0.0000

Data Index: 772171 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.6708. Min Act: -0.0000

Data Index: 70082 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1185345 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.5980. Min Act: -0.0000

Data Index: 608624 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.5325. Min Act: -0.0000

Data Index: 998393 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1358214 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1303594 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1209319 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4732. Min Act: -0.0000

Data Index: 1791 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4581. Min Act: -0.0000

Data Index: 15168 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4619. Min Act: -0.0000

Data Index: 761378 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1316850 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1188892 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4808. Min Act: -0.0000

Data Index: 742022 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4597. Min Act: -0.0000

Data Index: 246811 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4256. Min Act: -0.0000

Data Index: 640131 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4618. Min Act: -0.0000

Data Index: 204225 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4356. Min Act: -0.0000

Data Index: 900267 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4201. Min Act: -0.0000

Data Index: 456461 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4307. Min Act: -0.0000

Data Index: 451463 (C4 (Web Text))

Max Activating Token Index: 145