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

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

Neuron 2518 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.5280. Min Act: -0.0000

Data Index: 123320 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.3710. Min Act: -0.0000

Data Index: 742560 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.3100. Min Act: -0.0000

Data Index: 276580 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.3358. Min Act: -0.0000

Data Index: 240391 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1146883 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.3135. Min Act: -0.0000

Data Index: 458518 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2487. Min Act: -0.0000

Data Index: 562648 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2343. Min Act: -0.0000

Data Index: 1322340 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2136. Min Act: -0.0000

Data Index: 249296 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1260. Min Act: -0.0000

Data Index: 1274056 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2128. Min Act: -0.0000

Data Index: 336826 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1235. Min Act: -0.0000

Data Index: 1185491 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1280. Min Act: -0.0000

Data Index: 155619 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1332. Min Act: -0.0000

Data Index: 587162 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1202. Min Act: -0.0000

Data Index: 640067 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1122102 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1558. Min Act: -0.0000

Data Index: 192799 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1449. Min Act: -0.0000

Data Index: 432036 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.0806. Min Act: -0.0000

Data Index: 152258 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1045. Min Act: -0.0000

Data Index: 365339 (C4 (Web Text))

Max Activating Token Index: 626