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

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

Neuron 1965 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.6575. Min Act: -0.0001

Data Index: 1604302 (Python Code)

Max Activating Token Index: 572

Text #1

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5708. Min Act: -0.0001

Data Index: 1309397 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5503. Min Act: -0.0000

Data Index: 586711 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5618. Min Act: -0.0000

Data Index: 88017 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5435. Min Act: -0.0001

Data Index: 1377077 (Python Code)

Max Activating Token Index: 155

Text #5

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5517. Min Act: -0.0001

Data Index: 819569 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5256. Min Act: -0.0001

Data Index: 1621036 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5331. Min Act: -0.0001

Data Index: 1417521 (Python Code)

Max Activating Token Index: 537

Text #8

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4911. Min Act: -0.0000

Data Index: 225900 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5115. Min Act: -0.0001

Data Index: 376027 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4911. Min Act: -0.0000

Data Index: 282020 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1307690 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4818. Min Act: -0.0001

Data Index: 1653989 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4636. Min Act: -0.0001

Data Index: 999284 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4734. Min Act: -0.0001

Data Index: 1637889 (Python Code)

Max Activating Token Index: 389

Text #15

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4829. Min Act: -0.0001

Data Index: 1604062 (Python Code)

Max Activating Token Index: 730

Text #16

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4492. Min Act: -0.0000

Data Index: 280390 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4744. Min Act: -0.0000

Data Index: 742378 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4608. Min Act: -0.0001

Data Index: 1655506 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1097108 (C4 (Web Text))

Max Activating Token Index: 309