Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2484 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1951. Min Act: -0.0001

Data Index: 583329 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1842. Min Act: -0.0000

Data Index: 649096 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1812. Min Act: -0.0000

Data Index: 239947 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1757. Min Act: -0.0001

Data Index: 713339 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1697. Min Act: -0.0000

Data Index: 212838 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1598. Min Act: -0.0001

Data Index: 792931 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1662. Min Act: -0.0001

Data Index: 767356 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1661. Min Act: -0.0001

Data Index: 1642858 (Python Code)

Max Activating Token Index: 622

Text #8

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1323513 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1678. Min Act: -0.0001

Data Index: 240921 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1681. Min Act: -0.0001

Data Index: 949202 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1259232 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1202679 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1622. Min Act: 0.0000

Data Index: 316185 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1573. Min Act: -0.0001

Data Index: 43226 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1576. Min Act: 0.0000

Data Index: 574817 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1664. Min Act: -0.0001

Data Index: 738037 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1605. Min Act: -0.0001

Data Index: 17969 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1457. Min Act: -0.0001

Data Index: 389050 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1581857 (Python Code)

Max Activating Token Index: 512