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

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

Neuron 4803 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0002

Data Index: 569526 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1311982 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0675. Min Act: -0.0002

Data Index: 465022 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0640. Min Act: -0.0002

Data Index: 693844 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0672. Min Act: -0.0002

Data Index: 303294 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1237952 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0593. Min Act: -0.0002

Data Index: 440844 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0588. Min Act: -0.0002

Data Index: 189144 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0558. Min Act: -0.0002

Data Index: 599473 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1243129 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0519. Min Act: -0.0002

Data Index: 555343 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0511. Min Act: -0.0002

Data Index: 20435 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1136891 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0510. Min Act: -0.0002

Data Index: 427800 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0525. Min Act: -0.0002

Data Index: 983546 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1485279 (Python Code)

Max Activating Token Index: 489

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1070442 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0485. Min Act: -0.0002

Data Index: 9967 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0482. Min Act: -0.0002

Data Index: 120648 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0501. Min Act: -0.0002

Data Index: 762949 (C4 (Web Text))

Max Activating Token Index: 298