Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4561 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1406557 (Python Code)

Max Activating Token Index: 835

Text #1

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1389868 (Python Code)

Max Activating Token Index: 634

Text #2

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1495427 (Python Code)

Max Activating Token Index: 198

Text #3

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1649332 (Python Code)

Max Activating Token Index: 778

Text #4

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1373600 (Python Code)

Max Activating Token Index: 340

Text #5

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1257963 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1639468 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1534269 (Python Code)

Max Activating Token Index: 524

Text #8

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1637690 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1512621 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1390799 (Python Code)

Max Activating Token Index: 659

Text #11

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1512263 (Python Code)

Max Activating Token Index: 511

Text #12

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6210. Min Act: -0.0000

Data Index: 129887 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1633388 (Python Code)

Max Activating Token Index: 564

Text #14

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1501251 (Python Code)

Max Activating Token Index: 299

Text #15

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1520708 (Python Code)

Max Activating Token Index: 312

Text #16

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1587365 (Python Code)

Max Activating Token Index: 889

Text #17

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1419149 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6777. Min Act: -0.0000

Data Index: 506322 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.6362. Min Act: -0.0000

Data Index: 325409 (C4 (Web Text))

Max Activating Token Index: 358