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

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

Neuron 3845 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: 0.0436. Min Range: -0.0436

Max Act: 0.0422. Min Act: -0.0002

Data Index: 317323 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1151989 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0340. Min Act: -0.0002

Data Index: 563760 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1312786 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0361. Min Act: -0.0002

Data Index: 374577 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1260472 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0331. Min Act: -0.0002

Data Index: 264139 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1138231 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0314. Min Act: -0.0002

Data Index: 799411 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0320. Min Act: -0.0001

Data Index: 205539 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0307. Min Act: -0.0001

Data Index: 797180 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1243041 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1358609 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1093389 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1170672 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1601972 (Python Code)

Max Activating Token Index: 488

Text #16

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1274510 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0304. Min Act: -0.0001

Data Index: 657437 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0284. Min Act: -0.0002

Data Index: 939170 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0289. Min Act: -0.0002

Data Index: 595965 (C4 (Web Text))

Max Activating Token Index: 430