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

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

Neuron 5819 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2951. Min Act: -0.0002

Data Index: 1232926 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2586. Min Act: -0.0002

Data Index: 841698 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2267. Min Act: -0.0003

Data Index: 815428 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2500. Min Act: -0.0002

Data Index: 800001 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2207. Min Act: -0.0002

Data Index: 57370 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2021. Min Act: -0.0002

Data Index: 702286 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2175. Min Act: -0.0003

Data Index: 1298257 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2284. Min Act: -0.0002

Data Index: 1083226 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2121. Min Act: -0.0002

Data Index: 361940 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1793. Min Act: -0.0002

Data Index: 1206414 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1828. Min Act: -0.0002

Data Index: 825564 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1750. Min Act: -0.0002

Data Index: 303201 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1603. Min Act: -0.0003

Data Index: 739401 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1830. Min Act: -0.0003

Data Index: 427003 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1714. Min Act: -0.0002

Data Index: 160021 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1689. Min Act: -0.0002

Data Index: 366405 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1439. Min Act: -0.0002

Data Index: 1169714 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1381. Min Act: -0.0003

Data Index: 48663 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1317. Min Act: -0.0002

Data Index: 670093 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1338. Min Act: -0.0002

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 146