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

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

Neuron 2979 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: 0.2409. Min Range: -0.2409

Max Act: 0.2409. Min Act: -0.0000

Data Index: 900916 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.2114. Min Act: -0.0000

Data Index: 122228 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.2106. Min Act: -0.0000

Data Index: 654214 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.2161. Min Act: -0.0001

Data Index: 1153551 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.2075. Min Act: -0.0000

Data Index: 647336 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1844. Min Act: -0.0000

Data Index: 374447 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1751. Min Act: -0.0000

Data Index: 691703 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1777. Min Act: -0.0001

Data Index: 1226708 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1810. Min Act: -0.0000

Data Index: 350345 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1195952 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1666. Min Act: -0.0000

Data Index: 394180 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1706. Min Act: -0.0000

Data Index: 16166 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1621. Min Act: -0.0000

Data Index: 333778 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1093109 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1675. Min Act: -0.0000

Data Index: 85480 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1692. Min Act: -0.0000

Data Index: 681235 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1661. Min Act: -0.0000

Data Index: 389784 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1649. Min Act: -0.0000

Data Index: 582449 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1619. Min Act: -0.0000

Data Index: 947560 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1004240 (C4 (Web Text))

Max Activating Token Index: 186