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

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

Neuron 4543 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: 2.1571. Min Range: -2.1571

Max Act: 2.1571. Min Act: -0.0000

Data Index: 97418 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.7370. Min Act: -0.0000

Data Index: 40879 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.7770. Min Act: -0.0000

Data Index: 776306 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.7250. Min Act: -0.0000

Data Index: 456286 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.6188. Min Act: -0.0001

Data Index: 35843 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.6959. Min Act: -0.0000

Data Index: 440894 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.6392. Min Act: -0.0000

Data Index: 1418278 (Python Code)

Max Activating Token Index: 694

Text #7

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.6668. Min Act: -0.0000

Data Index: 610116 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.6607. Min Act: -0.0000

Data Index: 1213242 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5184. Min Act: -0.0000

Data Index: 813510 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5644. Min Act: -0.0000

Data Index: 1067034 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5037. Min Act: -0.0000

Data Index: 290816 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5118. Min Act: -0.0001

Data Index: 406556 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5433. Min Act: -0.0000

Data Index: 494594 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.4915. Min Act: -0.0000

Data Index: 178868 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5239. Min Act: -0.0000

Data Index: 1359445 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5703. Min Act: -0.0000

Data Index: 335875 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5239. Min Act: -0.0000

Data Index: 1112406 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5234. Min Act: -0.0000

Data Index: 1164291 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.4416. Min Act: -0.0000

Data Index: 178950 (C4 (Web Text))

Max Activating Token Index: 1007