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

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

Neuron 4401 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1506969 (Python Code)

Max Activating Token Index: 513

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1373450 (Python Code)

Max Activating Token Index: 194

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1626326 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1547079 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1613026 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0284. Min Act: -0.0003

Data Index: 58482 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1457646 (Python Code)

Max Activating Token Index: 926

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0276. Min Act: -0.0002

Data Index: 220082 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0274. Min Act: -0.0002

Data Index: 406795 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0277. Min Act: -0.0003

Data Index: 366458 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1021552 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1617932 (Python Code)

Max Activating Token Index: 314

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1342946 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1058563 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1098750 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1016095 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0273. Min Act: -0.0002

Data Index: 275866 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0260. Min Act: -0.0002

Data Index: 774121 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1547509 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0260. Min Act: -0.0003

Data Index: 700888 (C4 (Web Text))

Max Activating Token Index: 35