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

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

Neuron 4669 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1622. Min Range: -2.1622

Max Act: 2.1040. Min Act: -0.0000

Data Index: 1378462 (Python Code)

Max Activating Token Index: 201

Text #1

Max Range: 2.1622. Min Range: -2.1622

Max Act: 2.1622. Min Act: -0.0000

Data Index: 1627714 (Python Code)

Max Activating Token Index: 590

Text #2

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.7069. Min Act: -0.0000

Data Index: 701671 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.8322. Min Act: -0.0000

Data Index: 1558826 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.8730. Min Act: -0.0000

Data Index: 800284 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.7898. Min Act: -0.0000

Data Index: 1437195 (Python Code)

Max Activating Token Index: 462

Text #6

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.6481. Min Act: -0.0000

Data Index: 1235823 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.6179. Min Act: -0.0000

Data Index: 1480637 (Python Code)

Max Activating Token Index: 912

Text #8

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.5935. Min Act: -0.0000

Data Index: 1349123 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.5452. Min Act: -0.0000

Data Index: 971871 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.5015. Min Act: -0.0000

Data Index: 1636592 (Python Code)

Max Activating Token Index: 589

Text #11

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.4798. Min Act: -0.0001

Data Index: 1380456 (Python Code)

Max Activating Token Index: 701

Text #12

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.6077. Min Act: -0.0000

Data Index: 1225909 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.5652. Min Act: -0.0000

Data Index: 239878 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.6354. Min Act: -0.0000

Data Index: 896369 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.5422. Min Act: -0.0000

Data Index: 367020 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.5650. Min Act: -0.0000

Data Index: 861435 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.4421. Min Act: -0.0000

Data Index: 1434689 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.5770. Min Act: -0.0000

Data Index: 498393 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 2.1622. Min Range: -2.1622

Max Act: 1.7054. Min Act: -0.0000

Data Index: 1392758 (Python Code)

Max Activating Token Index: 1015