Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1917 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.4171. Min Act: -0.0001

Data Index: 1044394 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3569. Min Act: -0.0001

Data Index: 448420 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2659. Min Act: -0.0001

Data Index: 242321 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2477. Min Act: -0.0001

Data Index: 745764 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2747. Min Act: -0.0001

Data Index: 885799 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2256. Min Act: -0.0001

Data Index: 1189376 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2576. Min Act: -0.0001

Data Index: 60753 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2458. Min Act: -0.0002

Data Index: 1244015 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2008. Min Act: -0.0002

Data Index: 444355 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2606. Min Act: -0.0002

Data Index: 518428 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2250. Min Act: -0.0002

Data Index: 729629 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1325913 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2538. Min Act: -0.0002

Data Index: 327317 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2519. Min Act: -0.0002

Data Index: 900478 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2169. Min Act: -0.0001

Data Index: 214326 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2370. Min Act: -0.0001

Data Index: 582825 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2286. Min Act: -0.0002

Data Index: 248919 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2365. Min Act: -0.0002

Data Index: 574905 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2278. Min Act: -0.0001

Data Index: 1256702 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2407. Min Act: -0.0002

Data Index: 634819 (C4 (Web Text))

Max Activating Token Index: 850