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

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

Neuron 1926 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5809. Min Act: -0.0001

Data Index: 1475496 (Python Code)

Max Activating Token Index: 594

Text #1

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5891. Min Act: -0.0001

Data Index: 1584059 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5434. Min Act: -0.0001

Data Index: 1373318 (Python Code)

Max Activating Token Index: 282

Text #3

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1293830 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4358. Min Act: -0.0001

Data Index: 1605704 (Python Code)

Max Activating Token Index: 450

Text #5

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4404. Min Act: 0.0000

Data Index: 497526 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1318823 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4679. Min Act: -0.0000

Data Index: 176327 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4167. Min Act: -0.0001

Data Index: 1500225 (Python Code)

Max Activating Token Index: 511

Text #9

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4394. Min Act: -0.0001

Data Index: 1392050 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4555. Min Act: -0.0000

Data Index: 24481 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3922. Min Act: -0.0001

Data Index: 1419891 (Python Code)

Max Activating Token Index: 829

Text #12

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3839. Min Act: 0.0001

Data Index: 98218 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3978. Min Act: -0.0001

Data Index: 1547771 (Python Code)

Max Activating Token Index: 909

Text #14

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3971. Min Act: -0.0001

Data Index: 1465352 (Python Code)

Max Activating Token Index: 612

Text #15

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3796. Min Act: -0.0001

Data Index: 1548242 (Python Code)

Max Activating Token Index: 941

Text #16

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3819. Min Act: -0.0000

Data Index: 772076 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3471. Min Act: -0.0001

Data Index: 1519206 (Python Code)

Max Activating Token Index: 354

Text #18

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3551. Min Act: -0.0001

Data Index: 1652855 (Python Code)

Max Activating Token Index: 838

Text #19

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3337. Min Act: -0.0000

Data Index: 425584 (C4 (Web Text))

Max Activating Token Index: 172