Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4692 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1320436 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1300711 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2882. Min Act: -0.0000

Data Index: 671480 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2868. Min Act: -0.0000

Data Index: 633777 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2623. Min Act: -0.0000

Data Index: 165372 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2952. Min Act: -0.0000

Data Index: 902654 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2449. Min Act: -0.0000

Data Index: 659936 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1182066 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2516. Min Act: -0.0000

Data Index: 764214 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2592. Min Act: -0.0000

Data Index: 322314 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2668. Min Act: -0.0000

Data Index: 627997 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2413. Min Act: -0.0000

Data Index: 485781 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2462. Min Act: -0.0000

Data Index: 699326 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1253243 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2518. Min Act: -0.0000

Data Index: 659739 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2321. Min Act: -0.0000

Data Index: 207777 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1120771 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2467. Min Act: -0.0000

Data Index: 50618 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1143530 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.3556. Min Range: -0.3556

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1095989 (C4 (Web Text))

Max Activating Token Index: 218