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

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

Neuron 2001 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.8446. Min Act: -0.0000

Data Index: 491493 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6713. Min Act: -0.0000

Data Index: 758092 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6174. Min Act: -0.0000

Data Index: 329794 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6272. Min Act: -0.0000

Data Index: 707789 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5971. Min Act: -0.0000

Data Index: 758991 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6408. Min Act: -0.0000

Data Index: 294449 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1144910 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5831. Min Act: -0.0000

Data Index: 77641 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5864. Min Act: -0.0000

Data Index: 670839 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.6478. Min Act: -0.0000

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1240060 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1193520 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5667. Min Act: -0.0000

Data Index: 601292 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5443. Min Act: -0.0000

Data Index: 370279 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1136776 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1064836 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5477. Min Act: -0.0000

Data Index: 410163 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1063863 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.4958. Min Act: -0.0000

Data Index: 321155 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1187817 (C4 (Web Text))

Max Activating Token Index: 54