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

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

Neuron 992 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2364. Min Range: -1.2364

Max Act: 1.1781. Min Act: -0.0002

Data Index: 46491 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 1.2364. Min Range: -1.2364

Max Act: 1.2364. Min Act: -0.0001

Data Index: 827794 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 1.2364. Min Range: -1.2364

Max Act: 1.1546. Min Act: -0.0001

Data Index: 220305 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.9590. Min Act: -0.0002

Data Index: 1254723 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.9186. Min Act: -0.0002

Data Index: 875289 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.9763. Min Act: -0.0001

Data Index: 414181 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8906. Min Act: -0.0001

Data Index: 964380 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8828. Min Act: -0.0001

Data Index: 1030818 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8783. Min Act: -0.0001

Data Index: 278514 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8729. Min Act: -0.0002

Data Index: 490401 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8672. Min Act: -0.0001

Data Index: 177251 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8596. Min Act: -0.0001

Data Index: 378408 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8307. Min Act: -0.0001

Data Index: 432447 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8852. Min Act: -0.0001

Data Index: 860283 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8074. Min Act: -0.0001

Data Index: 433615 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8234. Min Act: -0.0002

Data Index: 609563 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8261. Min Act: -0.0002

Data Index: 608223 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8270. Min Act: -0.0001

Data Index: 633056 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8096. Min Act: -0.0002

Data Index: 26035 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8435. Min Act: -0.0002

Data Index: 807559 (C4 (Web Text))

Max Activating Token Index: 945