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

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

Neuron 3703 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: 0.1646. Min Range: -0.1646

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1653299 (Python Code)

Max Activating Token Index: 556

Text #1

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1547. Min Act: -0.0001

Data Index: 806614 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1070827 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1474. Min Act: -0.0002

Data Index: 1353504 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1533. Min Act: -0.0001

Data Index: 99531 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1487. Min Act: -0.0002

Data Index: 241429 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1417. Min Act: -0.0002

Data Index: 767069 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1446. Min Act: -0.0002

Data Index: 816203 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1385. Min Act: -0.0002

Data Index: 107639 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1389. Min Act: -0.0002

Data Index: 1291125 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1394. Min Act: -0.0002

Data Index: 1101382 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1373. Min Act: -0.0001

Data Index: 997469 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1376. Min Act: -0.0002

Data Index: 1060878 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1341. Min Act: -0.0002

Data Index: 988575 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1287. Min Act: -0.0002

Data Index: 845775 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1263. Min Act: -0.0002

Data Index: 817960 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1226. Min Act: -0.0001

Data Index: 785990 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1406. Min Act: -0.0002

Data Index: 276798 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1256894 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1482829 (Python Code)

Max Activating Token Index: 880