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

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

Neuron 4496 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7533. Min Act: 0.0000

Data Index: 1427799 (Python Code)

Max Activating Token Index: 253

Text #1

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.8448. Min Act: 0.0000

Data Index: 1538780 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1632581 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1600313 (Python Code)

Max Activating Token Index: 955

Text #4

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1375058 (Python Code)

Max Activating Token Index: 811

Text #5

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1365442 (Python Code)

Max Activating Token Index: 999

Text #6

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1464944 (Python Code)

Max Activating Token Index: 540

Text #7

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1615586 (Python Code)

Max Activating Token Index: 580

Text #8

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1438887 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1616916 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1408598 (Python Code)

Max Activating Token Index: 545

Text #11

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1387639 (Python Code)

Max Activating Token Index: 526

Text #12

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1642820 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1428436 (Python Code)

Max Activating Token Index: 771

Text #14

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1430364 (Python Code)

Max Activating Token Index: 733

Text #15

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6528. Min Act: 0.0000

Data Index: 1497447 (Python Code)

Max Activating Token Index: 337

Text #16

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1631310 (Python Code)

Max Activating Token Index: 692

Text #17

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1467560 (Python Code)

Max Activating Token Index: 969

Text #18

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1406002 (Python Code)

Max Activating Token Index: 710

Text #19

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1392280 (Python Code)

Max Activating Token Index: 316