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

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

Neuron 6018 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: 4.0462. Min Range: -4.0462

Max Act: 3.8450. Min Act: -0.0000

Data Index: 1619366 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 4.0462. Min Range: -4.0462

Max Act: 4.0462. Min Act: -0.0000

Data Index: 1618871 (Python Code)

Max Activating Token Index: 754

Text #2

Max Range: 4.0462. Min Range: -4.0462

Max Act: 3.6660. Min Act: -0.0000

Data Index: 1655085 (Python Code)

Max Activating Token Index: 702

Text #3

Max Range: 4.0462. Min Range: -4.0462

Max Act: 3.4652. Min Act: -0.0000

Data Index: 1403512 (Python Code)

Max Activating Token Index: 866

Text #4

Max Range: 4.0462. Min Range: -4.0462

Max Act: 3.2980. Min Act: -0.0000

Data Index: 1460148 (Python Code)

Max Activating Token Index: 566

Text #5

Max Range: 4.0462. Min Range: -4.0462

Max Act: 3.3176. Min Act: -0.0000

Data Index: 1497947 (Python Code)

Max Activating Token Index: 617

Text #6

Max Range: 4.0462. Min Range: -4.0462

Max Act: 3.6053. Min Act: -0.0000

Data Index: 1645906 (Python Code)

Max Activating Token Index: 726

Text #7

Max Range: 4.0462. Min Range: -4.0462

Max Act: 3.0188. Min Act: -0.0000

Data Index: 1378469 (Python Code)

Max Activating Token Index: 624

Text #8

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.8230. Min Act: -0.0000

Data Index: 1499194 (Python Code)

Max Activating Token Index: 785

Text #9

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.7722. Min Act: -0.0000

Data Index: 1452741 (Python Code)

Max Activating Token Index: 149

Text #10

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.9178. Min Act: -0.0000

Data Index: 1601916 (Python Code)

Max Activating Token Index: 905

Text #11

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.8931. Min Act: -0.0000

Data Index: 1465272 (Python Code)

Max Activating Token Index: 841

Text #12

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.6174. Min Act: -0.0000

Data Index: 1419484 (Python Code)

Max Activating Token Index: 695

Text #13

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.5442. Min Act: -0.0000

Data Index: 1545141 (Python Code)

Max Activating Token Index: 399

Text #14

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.6550. Min Act: -0.0000

Data Index: 1453479 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.7755. Min Act: -0.0000

Data Index: 1502219 (Python Code)

Max Activating Token Index: 264

Text #16

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.3763. Min Act: -0.0000

Data Index: 1452394 (Python Code)

Max Activating Token Index: 706

Text #17

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.1222. Min Act: -0.0000

Data Index: 1517574 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.0526. Min Act: -0.0000

Data Index: 1646674 (Python Code)

Max Activating Token Index: 618

Text #19

Max Range: 4.0462. Min Range: -4.0462

Max Act: 2.0803. Min Act: -0.0000

Data Index: 1510204 (Python Code)

Max Activating Token Index: 889