Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4056 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1868. Min Act: -0.0001

Data Index: 762535 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1006289 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1770. Min Act: -0.0001

Data Index: 161490 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1830. Min Act: -0.0001

Data Index: 16428 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1764. Min Act: -0.0001

Data Index: 602886 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1737. Min Act: -0.0001

Data Index: 813235 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1771. Min Act: -0.0001

Data Index: 293536 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1791. Min Act: -0.0001

Data Index: 772074 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1668. Min Act: -0.0001

Data Index: 621775 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1652. Min Act: -0.0001

Data Index: 369710 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1153307 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1624. Min Act: -0.0002

Data Index: 45447 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1621. Min Act: -0.0001

Data Index: 859790 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1588. Min Act: -0.0001

Data Index: 83298 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1595. Min Act: -0.0001

Data Index: 244352 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1562. Min Act: -0.0001

Data Index: 349068 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1388. Min Act: -0.0001

Data Index: 716858 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1056243 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.0265. Min Act: -0.0001

Data Index: 267251 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.0214. Min Act: -0.0001

Data Index: 557185 (C4 (Web Text))

Max Activating Token Index: 460