Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 274 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.9562. Min Act: -0.0001

Data Index: 892790 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.0551. Min Act: -0.0001

Data Index: 247908 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.0510. Min Act: -0.0001

Data Index: 1358592 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.8206. Min Act: -0.0001

Data Index: 636245 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.0003. Min Act: -0.0001

Data Index: 725691 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.9539. Min Act: -0.0001

Data Index: 624606 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.4587. Min Act: -0.0001

Data Index: 619386 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.8425. Min Act: -0.0001

Data Index: 157310 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.0499. Min Act: -0.0001

Data Index: 1264197 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.5232. Min Act: -0.0001

Data Index: 683334 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.6436. Min Act: -0.0001

Data Index: 410179 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.0758. Min Act: -0.0001

Data Index: 731706 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.4986. Min Act: -0.0001

Data Index: 334261 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.6349. Min Act: -0.0001

Data Index: 1182010 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.6058. Min Act: -0.0001

Data Index: 257637 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.4468. Min Act: -0.0001

Data Index: 1073351 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.2141. Min Act: -0.0001

Data Index: 787695 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.2879. Min Act: -0.0001

Data Index: 1032535 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.1067. Min Act: -0.0001

Data Index: 1206465 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.0687. Min Act: -0.0001

Data Index: 539261 (C4 (Web Text))

Max Activating Token Index: 933