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

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

Neuron 1422 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: 0.6495. Min Range: -0.6495

Max Act: 0.6495. Min Act: -0.0000

Data Index: 677643 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6029. Min Act: -0.0000

Data Index: 598639 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6179. Min Act: -0.0001

Data Index: 257310 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5839. Min Act: -0.0001

Data Index: 1090256 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5655. Min Act: -0.0001

Data Index: 150322 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1228802 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5798. Min Act: -0.0001

Data Index: 1336597 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5633. Min Act: -0.0001

Data Index: 1125060 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5577. Min Act: -0.0000

Data Index: 361653 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5172. Min Act: -0.0000

Data Index: 40342 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5212. Min Act: -0.0000

Data Index: 861219 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.4862. Min Act: -0.0000

Data Index: 296133 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.4959. Min Act: -0.0001

Data Index: 180470 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5330. Min Act: -0.0000

Data Index: 320889 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5108. Min Act: -0.0000

Data Index: 432862 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.4906. Min Act: -0.0001

Data Index: 223575 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5089. Min Act: -0.0000

Data Index: 293546 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5033. Min Act: -0.0000

Data Index: 911458 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.4821. Min Act: -0.0001

Data Index: 827982 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5105. Min Act: -0.0000

Data Index: 583672 (C4 (Web Text))

Max Activating Token Index: 781