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

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

Neuron 489 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: 0.0514. Min Range: -0.0514

Max Act: 0.0514. Min Act: -0.0003

Data Index: 393150 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0500. Min Act: -0.0003

Data Index: 648383 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0512. Min Act: -0.0003

Data Index: 492887 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1151605 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0487. Min Act: -0.0004

Data Index: 255707 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0483. Min Act: -0.0003

Data Index: 228033 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0482. Min Act: -0.0003

Data Index: 234633 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0479. Min Act: -0.0003

Data Index: 216268 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0482. Min Act: -0.0004

Data Index: 1191370 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0481. Min Act: -0.0003

Data Index: 78188 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0462. Min Act: -0.0003

Data Index: 784282 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0458. Min Act: -0.0003

Data Index: 703847 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0450. Min Act: -0.0003

Data Index: 652113 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1333 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0446. Min Act: -0.0003

Data Index: 964805 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0453. Min Act: -0.0003

Data Index: 4234 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1283161 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0449. Min Act: -0.0002

Data Index: 80985 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0442. Min Act: -0.0003

Data Index: 535382 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0451. Min Act: -0.0003

Data Index: 654759 (C4 (Web Text))

Max Activating Token Index: 249