Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2714 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0461. Min Act: -0.0004

Data Index: 415642 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0343. Min Act: -0.0004

Data Index: 1202518 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0373. Min Act: -0.0004

Data Index: 1290991 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0358. Min Act: -0.0004

Data Index: 1312610 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0323. Min Act: -0.0004

Data Index: 92584 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0318. Min Act: -0.0004

Data Index: 702913 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0312. Min Act: -0.0004

Data Index: 306425 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0303. Min Act: -0.0004

Data Index: 949409 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1204586 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0252. Min Act: -0.0004

Data Index: 1218623 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0298. Min Act: -0.0004

Data Index: 23359 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0284. Min Act: -0.0004

Data Index: 1351549 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0309. Min Act: -0.0004

Data Index: 944360 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0294. Min Act: -0.0004

Data Index: 1638273 (Python Code)

Max Activating Token Index: 646

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0295. Min Act: -0.0004

Data Index: 517313 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0287. Min Act: -0.0004

Data Index: 1273771 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0283. Min Act: -0.0004

Data Index: 776839 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0312. Min Act: -0.0004

Data Index: 1057023 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0317. Min Act: -0.0004

Data Index: 367337 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0303. Min Act: -0.0004

Data Index: 1276083 (C4 (Web Text))

Max Activating Token Index: 505