Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2060 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.5205. Min Act: -0.0000

Data Index: 736330 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1456798 (Python Code)

Max Activating Token Index: 304

Text #2

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.4949. Min Act: -0.0000

Data Index: 946547 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.4595. Min Act: -0.0000

Data Index: 344152 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.4713. Min Act: -0.0000

Data Index: 274261 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.4367. Min Act: -0.0000

Data Index: 711270 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1432857 (Python Code)

Max Activating Token Index: 635

Text #7

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.4084. Min Act: -0.0000

Data Index: 826766 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1200597 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1093835 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3848. Min Act: -0.0000

Data Index: 53534 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1430343 (Python Code)

Max Activating Token Index: 826

Text #12

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3838. Min Act: -0.0000

Data Index: 210532 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3764. Min Act: -0.0000

Data Index: 123468 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3751. Min Act: -0.0000

Data Index: 528312 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3657. Min Act: -0.0000

Data Index: 13506 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1426836 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3744. Min Act: -0.0000

Data Index: 862513 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3709. Min Act: -0.0000

Data Index: 922872 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.5205. Min Range: -0.5205

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1592659 (Python Code)

Max Activating Token Index: 237