Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6118 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.5553. Min Act: -0.0000

Data Index: 1235559 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1415965 (Python Code)

Max Activating Token Index: 855

Text #2

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.3492. Min Act: -0.0000

Data Index: 516017 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1407853 (Python Code)

Max Activating Token Index: 980

Text #4

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.3319. Min Act: -0.0000

Data Index: 360193 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.2778. Min Act: -0.0000

Data Index: 743397 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1362566 (Python Code)

Max Activating Token Index: 464

Text #7

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.2507. Min Act: -0.0000

Data Index: 1030894 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1407. Min Act: -0.0000

Data Index: 216926 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1625047 (Python Code)

Max Activating Token Index: 896

Text #10

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1483689 (Python Code)

Max Activating Token Index: 1008

Text #11

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1798. Min Act: -0.0000

Data Index: 637139 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1134. Min Act: -0.0000

Data Index: 1460012 (Python Code)

Max Activating Token Index: 600

Text #13

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1048. Min Act: -0.0000

Data Index: 41260 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1262223 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.1563. Min Act: -0.0000

Data Index: 945132 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 1.5553. Min Range: -1.5553

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1530601 (Python Code)

Max Activating Token Index: 820

Text #17

Max Range: 1.5553. Min Range: -1.5553

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1623852 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 1.5553. Min Range: -1.5553

Max Act: 1.0102. Min Act: -0.0000

Data Index: 1459140 (Python Code)

Max Activating Token Index: 338

Text #19

Max Range: 1.5553. Min Range: -1.5553

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1618394 (Python Code)

Max Activating Token Index: 62