Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2991 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.7783. Min Act: -0.0002

Data Index: 1073736 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5399. Min Act: -0.0001

Data Index: 1542524 (Python Code)

Max Activating Token Index: 714

Text #2

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5362. Min Act: -0.0001

Data Index: 1614486 (Python Code)

Max Activating Token Index: 88

Text #3

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5170. Min Act: -0.0001

Data Index: 1539847 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5047. Min Act: -0.0002

Data Index: 905783 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4954. Min Act: -0.0001

Data Index: 763071 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4829. Min Act: -0.0001

Data Index: 1623219 (Python Code)

Max Activating Token Index: 381

Text #7

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4705. Min Act: -0.0001

Data Index: 732559 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4659. Min Act: -0.0002

Data Index: 81739 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4797. Min Act: -0.0001

Data Index: 178218 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4747. Min Act: -0.0001

Data Index: 1421868 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4443. Min Act: -0.0001

Data Index: 1453128 (Python Code)

Max Activating Token Index: 348

Text #12

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4737. Min Act: -0.0001

Data Index: 433382 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4326. Min Act: -0.0001

Data Index: 1482770 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4900. Min Act: -0.0001

Data Index: 1378118 (Python Code)

Max Activating Token Index: 483

Text #15

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4548. Min Act: -0.0002

Data Index: 1474406 (Python Code)

Max Activating Token Index: 858

Text #16

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4461. Min Act: -0.0001

Data Index: 1513503 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1616716 (Python Code)

Max Activating Token Index: 795

Text #18

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4952. Min Act: -0.0002

Data Index: 747962 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.4486. Min Act: -0.0001

Data Index: 1518117 (Python Code)

Max Activating Token Index: 919