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

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

Neuron 2519 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: 1.2633. Min Range: -1.2633

Max Act: 1.2499. Min Act: -0.0000

Data Index: 716463 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.2633. Min Range: -1.2633

Max Act: 1.2633. Min Act: -0.0000

Data Index: 887965 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.7804. Min Act: -0.0000

Data Index: 928808 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.7168. Min Act: -0.0000

Data Index: 137652 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6377. Min Act: -0.0000

Data Index: 715928 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6376. Min Act: -0.0000

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1304061 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.5877. Min Act: -0.0000

Data Index: 118995 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.5823. Min Act: -0.0000

Data Index: 676269 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1121496 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.5410. Min Act: -0.0000

Data Index: 822027 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.5213. Min Act: -0.0000

Data Index: 507284 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.5211. Min Act: -0.0000

Data Index: 878019 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.5181. Min Act: -0.0000

Data Index: 120900 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.4679. Min Act: -0.0000

Data Index: 885673 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.5037. Min Act: -0.0000

Data Index: 220526 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.4580. Min Act: -0.0000

Data Index: 900326 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.4936. Min Act: -0.0000

Data Index: 689389 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.4587. Min Act: -0.0000

Data Index: 247866 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.4786. Min Act: -0.0000

Data Index: 414470 (C4 (Web Text))

Max Activating Token Index: 241