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

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

Neuron 3426 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0885. Min Range: -4.0885

Max Act: 4.0885. Min Act: -0.0000

Data Index: 460109 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.7513. Min Act: -0.0000

Data Index: 113582 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.4656. Min Act: -0.0000

Data Index: 706443 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.2096. Min Act: -0.0000

Data Index: 180150 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.3559. Min Act: -0.0000

Data Index: 7614 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.6308. Min Act: -0.0000

Data Index: 719857 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.4503. Min Act: -0.0000

Data Index: 736758 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.6120. Min Act: -0.0000

Data Index: 619968 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.4251. Min Act: -0.0000

Data Index: 743336 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.4265. Min Act: -0.0000

Data Index: 165472 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.1436. Min Act: -0.0000

Data Index: 502381 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.1256. Min Act: -0.0000

Data Index: 1048929 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 4.0885. Min Range: -4.0885

Max Act: 2.9501. Min Act: -0.0000

Data Index: 716203 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 4.0885. Min Range: -4.0885

Max Act: 2.9378. Min Act: -0.0000

Data Index: 972954 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.1602. Min Act: -0.0000

Data Index: 140958 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 4.0885. Min Range: -4.0885

Max Act: 2.8330. Min Act: -0.0000

Data Index: 411922 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 4.0885. Min Range: -4.0885

Max Act: 2.9401. Min Act: -0.0000

Data Index: 1072833 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.1304. Min Act: -0.0000

Data Index: 1047405 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 4.0885. Min Range: -4.0885

Max Act: 2.8582. Min Act: -0.0000

Data Index: 1161651 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 4.0885. Min Range: -4.0885

Max Act: 2.8182. Min Act: -0.0000

Data Index: 782893 (C4 (Web Text))

Max Activating Token Index: 441