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

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

Neuron 782 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.7709. Min Act: -0.0001

Data Index: 626526 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6943. Min Act: -0.0001

Data Index: 139668 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1126431 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5980. Min Act: -0.0001

Data Index: 38750 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6243. Min Act: -0.0001

Data Index: 702255 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5799. Min Act: -0.0001

Data Index: 874192 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5971. Min Act: -0.0001

Data Index: 662981 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5348. Min Act: -0.0001

Data Index: 1600814 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5515. Min Act: -0.0001

Data Index: 418292 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5621. Min Act: -0.0001

Data Index: 1495279 (Python Code)

Max Activating Token Index: 301

Text #10

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5281. Min Act: -0.0001

Data Index: 1149538 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5534. Min Act: -0.0001

Data Index: 252300 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.4913. Min Act: -0.0001

Data Index: 1649376 (Python Code)

Max Activating Token Index: 1014

Text #13

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5172. Min Act: -0.0001

Data Index: 395472 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5320. Min Act: -0.0001

Data Index: 272516 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5976. Min Act: -0.0001

Data Index: 1037661 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5487. Min Act: -0.0001

Data Index: 1643123 (Python Code)

Max Activating Token Index: 196

Text #17

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5234. Min Act: -0.0001

Data Index: 1337424 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5605. Min Act: -0.0001

Data Index: 707977 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5555. Min Act: -0.0001

Data Index: 852943 (C4 (Web Text))

Max Activating Token Index: 858