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

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

Neuron 1053 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: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1003149 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0347. Min Act: -0.0002

Data Index: 572603 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0322. Min Act: -0.0002

Data Index: 368113 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0315. Min Act: -0.0002

Data Index: 127498 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0304. Min Act: -0.0002

Data Index: 22609 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1323912 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1006274 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0287. Min Act: -0.0002

Data Index: 173131 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0289. Min Act: -0.0002

Data Index: 440477 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1315758 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0257. Min Act: -0.0002

Data Index: 99867 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0258. Min Act: -0.0002

Data Index: 230834 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0292. Min Act: -0.0002

Data Index: 6761 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0276. Min Act: -0.0002

Data Index: 74163 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0266. Min Act: -0.0002

Data Index: 146069 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0256. Min Act: -0.0002

Data Index: 380913 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0252. Min Act: -0.0002

Data Index: 6595 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0260. Min Act: -0.0002

Data Index: 822251 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0235. Min Act: -0.0002

Data Index: 115717 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0254. Min Act: -0.0002

Data Index: 2189 (C4 (Web Text))

Max Activating Token Index: 540