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

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

Neuron 289 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: 0.0625. Min Range: -0.0625

Max Act: 0.0625. Min Act: -0.0002

Data Index: 852541 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0620. Min Act: -0.0002

Data Index: 179592 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1008663 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0603. Min Act: -0.0002

Data Index: 842564 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0585. Min Act: -0.0002

Data Index: 782900 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0577. Min Act: -0.0002

Data Index: 193768 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0569. Min Act: -0.0002

Data Index: 991038 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1247025 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0532. Min Act: -0.0002

Data Index: 125649 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0566. Min Act: -0.0002

Data Index: 643142 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0561. Min Act: -0.0002

Data Index: 706785 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0554. Min Act: -0.0002

Data Index: 578676 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1177424 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0550. Min Act: -0.0002

Data Index: 177451 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0529. Min Act: -0.0002

Data Index: 995631 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0542. Min Act: -0.0002

Data Index: 90699 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1248227 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0522. Min Act: -0.0002

Data Index: 873576 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0539. Min Act: -0.0002

Data Index: 131189 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1021209 (C4 (Web Text))

Max Activating Token Index: 161