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

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

Neuron 2824 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0002

Data Index: 745984 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0696. Min Act: -0.0002

Data Index: 526595 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0619. Min Act: -0.0002

Data Index: 638547 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0680. Min Act: -0.0002

Data Index: 484628 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0597. Min Act: -0.0002

Data Index: 797229 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0633. Min Act: -0.0002

Data Index: 248761 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0588. Min Act: -0.0002

Data Index: 519338 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1089133 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0486. Min Act: -0.0002

Data Index: 669133 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1170206 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0542. Min Act: -0.0002

Data Index: 922875 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0677. Min Act: -0.0002

Data Index: 177254 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0467. Min Act: -0.0002

Data Index: 279179 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0593. Min Act: -0.0002

Data Index: 347959 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0634. Min Act: -0.0002

Data Index: 808593 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1323883 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0613. Min Act: -0.0002

Data Index: 858792 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0578. Min Act: -0.0002

Data Index: 794065 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1275613 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1007081 (C4 (Web Text))

Max Activating Token Index: 252