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

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

Neuron 3499 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1566654 (Python Code)

Max Activating Token Index: 980

Text #1

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.3321. Min Act: -0.0000

Data Index: 1362437 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.3055. Min Act: -0.0001

Data Index: 1607540 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1620207 (Python Code)

Max Activating Token Index: 477

Text #4

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1427325 (Python Code)

Max Activating Token Index: 292

Text #5

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1626253 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.1018. Min Act: -0.0000

Data Index: 1370934 (Python Code)

Max Activating Token Index: 128

Text #7

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.0603. Min Act: -0.0000

Data Index: 889999 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.0952. Min Act: -0.0000

Data Index: 134932 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1447863 (Python Code)

Max Activating Token Index: 699

Text #10

Max Range: 1.3321. Min Range: -1.3321

Max Act: 0.9616. Min Act: -0.0000

Data Index: 29042 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 1.3321. Min Range: -1.3321

Max Act: 0.9887. Min Act: -0.0000

Data Index: 933681 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.0451. Min Act: -0.0000

Data Index: 1394852 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.0404. Min Act: -0.0000

Data Index: 132960 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 1.3321. Min Range: -1.3321

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1387473 (Python Code)

Max Activating Token Index: 508

Text #15

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.0480. Min Act: -0.0000

Data Index: 1405041 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 1.3321. Min Range: -1.3321

Max Act: 0.8743. Min Act: -0.0001

Data Index: 1429110 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.0234. Min Act: -0.0000

Data Index: 828577 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.3321. Min Range: -1.3321

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1569271 (Python Code)

Max Activating Token Index: 324

Text #19

Max Range: 1.3321. Min Range: -1.3321

Max Act: 1.0047. Min Act: -0.0001

Data Index: 1460504 (Python Code)

Max Activating Token Index: 567