Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1551 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1202330 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0557. Min Act: -0.0002

Data Index: 842485 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0514. Min Act: -0.0002

Data Index: 718886 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0506. Min Act: -0.0002

Data Index: 300674 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0517. Min Act: -0.0002

Data Index: 174302 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0507. Min Act: -0.0001

Data Index: 201484 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1042306 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0503. Min Act: -0.0001

Data Index: 251778 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1010827 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0494. Min Act: -0.0001

Data Index: 584081 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0504. Min Act: -0.0002

Data Index: 941656 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0493. Min Act: -0.0002

Data Index: 19927 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0482. Min Act: -0.0001

Data Index: 940697 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0478. Min Act: -0.0001

Data Index: 906753 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1003984 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0474. Min Act: -0.0001

Data Index: 862007 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0472. Min Act: -0.0001

Data Index: 629017 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0462. Min Act: -0.0001

Data Index: 363476 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0469. Min Act: -0.0002

Data Index: 118012 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0457. Min Act: -0.0002

Data Index: 486250 (C4 (Web Text))

Max Activating Token Index: 87