Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 392 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0619. Min Act: -0.0003

Data Index: 357451 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0565. Min Act: -0.0003

Data Index: 509960 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0536. Min Act: -0.0003

Data Index: 517251 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0514. Min Act: -0.0003

Data Index: 897588 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0495. Min Act: -0.0003

Data Index: 562084 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0490. Min Act: -0.0003

Data Index: 721333 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0476. Min Act: -0.0003

Data Index: 842010 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0467. Min Act: -0.0003

Data Index: 878286 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0472. Min Act: -0.0003

Data Index: 943651 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0451. Min Act: -0.0003

Data Index: 951136 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0460. Min Act: -0.0003

Data Index: 630825 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1159632 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1075570 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0460. Min Act: -0.0003

Data Index: 45825 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0453. Min Act: -0.0003

Data Index: 571853 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0449. Min Act: -0.0003

Data Index: 706130 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0451. Min Act: -0.0003

Data Index: 357323 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1150606 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0464. Min Act: -0.0003

Data Index: 582129 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0436. Min Act: -0.0003

Data Index: 137171 (C4 (Web Text))

Max Activating Token Index: 140