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

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

Neuron 2988 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0409. Min Range: -1.0409

Max Act: 1.0409. Min Act: -0.0001

Data Index: 446452 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9973. Min Act: -0.0000

Data Index: 1307683 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 1.0409. Min Range: -1.0409

Max Act: 1.0252. Min Act: -0.0001

Data Index: 566175 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 1.0409. Min Range: -1.0409

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1092982 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9772. Min Act: -0.0001

Data Index: 169504 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 1.0409. Min Range: -1.0409

Max Act: 1.0046. Min Act: -0.0001

Data Index: 964760 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9920. Min Act: -0.0000

Data Index: 915622 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9820. Min Act: -0.0001

Data Index: 89305 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9607. Min Act: -0.0001

Data Index: 844623 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9320. Min Act: -0.0001

Data Index: 673720 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9681. Min Act: -0.0000

Data Index: 686716 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9287. Min Act: -0.0001

Data Index: 402387 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9045. Min Act: -0.0001

Data Index: 91695 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9145. Min Act: -0.0000

Data Index: 846377 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8895. Min Act: -0.0001

Data Index: 641484 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8867. Min Act: -0.0001

Data Index: 697605 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8182. Min Act: -0.0001

Data Index: 588003 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9060. Min Act: -0.0000

Data Index: 943650 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9253. Min Act: -0.0000

Data Index: 134075 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8929. Min Act: -0.0001

Data Index: 140627 (C4 (Web Text))

Max Activating Token Index: 477