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

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

Neuron 996 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: 0.0646. Min Range: -0.0646

Max Act: 0.0646. Min Act: -0.0002

Data Index: 12963 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0634. Min Act: -0.0002

Data Index: 82278 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0606. Min Act: -0.0002

Data Index: 643835 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0589. Min Act: -0.0003

Data Index: 766101 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1121691 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0581. Min Act: -0.0003

Data Index: 211711 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1062265 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0559. Min Act: -0.0002

Data Index: 248455 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0545. Min Act: -0.0002

Data Index: 317804 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0559. Min Act: -0.0002

Data Index: 923964 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0548. Min Act: -0.0003

Data Index: 662205 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1205776 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0540. Min Act: -0.0004

Data Index: 1263942 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0550. Min Act: -0.0002

Data Index: 33911 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0539. Min Act: -0.0002

Data Index: 806880 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0533. Min Act: -0.0002

Data Index: 343957 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1235445 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1259099 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0533. Min Act: -0.0002

Data Index: 202218 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0532. Min Act: -0.0002

Data Index: 118536 (C4 (Web Text))

Max Activating Token Index: 710