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

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

Neuron 3825 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: 0.1715. Min Range: -0.1715

Max Act: 0.1383. Min Act: -0.0002

Data Index: 745337 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1715. Min Act: -0.0002

Data Index: 252774 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1096281 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1635. Min Act: -0.0002

Data Index: 170285 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1382. Min Act: -0.0001

Data Index: 553323 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1287351 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1328. Min Act: -0.0001

Data Index: 467061 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1181. Min Act: -0.0002

Data Index: 75039 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1313. Min Act: -0.0002

Data Index: 556264 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1323. Min Act: -0.0002

Data Index: 1021531 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1214019 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1348. Min Act: -0.0001

Data Index: 741826 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1259. Min Act: -0.0002

Data Index: 705341 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1170. Min Act: -0.0002

Data Index: 840463 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1058389 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1304. Min Act: -0.0001

Data Index: 690033 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1014804 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1266. Min Act: -0.0002

Data Index: 548039 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1232. Min Act: -0.0002

Data Index: 961714 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1220136 (C4 (Web Text))

Max Activating Token Index: 841