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

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

Neuron 4813 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.4043. Min Act: -0.0002

Data Index: 57777 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.4422. Min Act: -0.0002

Data Index: 554863 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.2172. Min Act: -0.0002

Data Index: 100010 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.3130. Min Act: -0.0002

Data Index: 1275106 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1932. Min Act: -0.0002

Data Index: 416583 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1707. Min Act: -0.0002

Data Index: 29285 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.2609. Min Act: -0.0002

Data Index: 675761 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.2981. Min Act: -0.0002

Data Index: 895889 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1384. Min Act: -0.0002

Data Index: 238481 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1770. Min Act: -0.0002

Data Index: 859842 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1639. Min Act: -0.0002

Data Index: 465663 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9021. Min Act: -0.0002

Data Index: 364241 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1623. Min Act: -0.0002

Data Index: 131847 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0481. Min Act: -0.0002

Data Index: 258330 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1308. Min Act: -0.0002

Data Index: 91553 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1319. Min Act: -0.0002

Data Index: 1272249 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9840. Min Act: -0.0002

Data Index: 809272 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0548. Min Act: -0.0002

Data Index: 71477 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.8906. Min Act: -0.0002

Data Index: 203310 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0759. Min Act: -0.0002

Data Index: 58259 (C4 (Web Text))

Max Activating Token Index: 687