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

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

Neuron 2028 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: 1.0588. Min Range: -1.0588

Max Act: 1.0231. Min Act: -0.0000

Data Index: 808136 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 1.0588. Min Range: -1.0588

Max Act: 1.0588. Min Act: -0.0000

Data Index: 625300 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 1.0588. Min Range: -1.0588

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1047387 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.9487. Min Act: -0.0000

Data Index: 970370 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.9870. Min Act: -0.0000

Data Index: 573195 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.9376. Min Act: -0.0000

Data Index: 757495 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.9526. Min Act: -0.0000

Data Index: 179008 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.0588. Min Range: -1.0588

Max Act: 1.0433. Min Act: -0.0000

Data Index: 850167 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.8979. Min Act: -0.0000

Data Index: 896309 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.8247. Min Act: -0.0000

Data Index: 384128 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.8445. Min Act: -0.0000

Data Index: 400396 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1080045 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1267831 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1216904 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.7555. Min Act: -0.0000

Data Index: 694841 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1184169 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.7452. Min Act: -0.0000

Data Index: 406715 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.7541. Min Act: -0.0000

Data Index: 825069 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.7692. Min Act: -0.0000

Data Index: 119633 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 1.0588. Min Range: -1.0588

Max Act: 0.6394. Min Act: -0.0000

Data Index: 94807 (C4 (Web Text))

Max Activating Token Index: 532