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

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

Neuron 1395 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1481149 (Python Code)

Max Activating Token Index: 386

Text #1

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1444977 (Python Code)

Max Activating Token Index: 459

Text #2

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1367640 (Python Code)

Max Activating Token Index: 640

Text #3

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1369017 (Python Code)

Max Activating Token Index: 875

Text #4

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1381499 (Python Code)

Max Activating Token Index: 779

Text #5

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1654857 (Python Code)

Max Activating Token Index: 649

Text #6

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1583949 (Python Code)

Max Activating Token Index: 360

Text #7

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1442790 (Python Code)

Max Activating Token Index: 715

Text #8

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1196884 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1567530 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1504288 (Python Code)

Max Activating Token Index: 463

Text #11

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4497. Min Act: -0.0000

Data Index: 494269 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1517109 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1169354 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4300. Min Act: -0.0000

Data Index: 226309 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4253. Min Act: -0.0000

Data Index: 354037 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4241. Min Act: -0.0000

Data Index: 841545 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4360. Min Act: -0.0000

Data Index: 59894 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4327. Min Act: -0.0000

Data Index: 611773 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1349013 (C4 (Web Text))

Max Activating Token Index: 314