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

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

Neuron 1905 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: 0.0713. Min Range: -0.0713

Max Act: 0.0713. Min Act: -0.0002

Data Index: 249387 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0669. Min Act: -0.0002

Data Index: 643863 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0659. Min Act: -0.0002

Data Index: 406521 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0658. Min Act: -0.0002

Data Index: 336931 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0654. Min Act: -0.0002

Data Index: 954616 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0646. Min Act: -0.0002

Data Index: 811927 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0659. Min Act: -0.0001

Data Index: 878220 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0608. Min Act: -0.0002

Data Index: 18545 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1166976 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0614. Min Act: -0.0001

Data Index: 217983 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1050801 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0639. Min Act: -0.0002

Data Index: 220572 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0627. Min Act: -0.0002

Data Index: 226207 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0616. Min Act: -0.0002

Data Index: 481113 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1119834 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1145630 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0604. Min Act: -0.0001

Data Index: 893381 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0611. Min Act: -0.0002

Data Index: 447280 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0567. Min Act: -0.0002

Data Index: 667256 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1321180 (C4 (Web Text))

Max Activating Token Index: 316