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

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

Neuron 4501 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1422812 (Python Code)

Max Activating Token Index: 265

Text #1

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0315. Min Act: -0.0000

Data Index: 1398698 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0300. Min Act: -0.0001

Data Index: 730152 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1509706 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1557882 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0294. Min Act: -0.0001

Data Index: 1503298 (Python Code)

Max Activating Token Index: 334

Text #6

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1168729 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1440028 (Python Code)

Max Activating Token Index: 102

Text #8

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1535062 (Python Code)

Max Activating Token Index: 637

Text #9

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1399290 (Python Code)

Max Activating Token Index: 648

Text #10

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1507433 (Python Code)

Max Activating Token Index: 683

Text #11

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1528512 (Python Code)

Max Activating Token Index: 527

Text #12

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1401244 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0278. Min Act: -0.0001

Data Index: 34710 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0276. Min Act: -0.0001

Data Index: 435612 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0275. Min Act: -0.0000

Data Index: 1579434 (Python Code)

Max Activating Token Index: 470

Text #16

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1565507 (Python Code)

Max Activating Token Index: 557

Text #17

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1539029 (Python Code)

Max Activating Token Index: 220

Text #18

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1435574 (Python Code)

Max Activating Token Index: 510

Text #19

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0277. Min Act: -0.0000

Data Index: 1475575 (Python Code)

Max Activating Token Index: 580