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

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

Neuron 597 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1960. Min Act: -0.0001

Data Index: 1395437 (Python Code)

Max Activating Token Index: 997

Text #1

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1445064 (Python Code)

Max Activating Token Index: 460

Text #2

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1454187 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1488. Min Act: -0.0001

Data Index: 810431 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1476. Min Act: -0.0001

Data Index: 562304 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1500. Min Act: -0.0001

Data Index: 456914 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1350. Min Act: -0.0001

Data Index: 890084 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1329. Min Act: -0.0001

Data Index: 327330 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1317. Min Act: -0.0001

Data Index: 532337 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1301. Min Act: -0.0001

Data Index: 591656 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1264. Min Act: -0.0001

Data Index: 762932 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1625739 (Python Code)

Max Activating Token Index: 991

Text #12

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1221. Min Act: -0.0001

Data Index: 748207 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1303. Min Act: -0.0001

Data Index: 174153 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1158. Min Act: -0.0001

Data Index: 341363 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1256. Min Act: -0.0001

Data Index: 471909 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1162585 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1469219 (Python Code)

Max Activating Token Index: 453

Text #18

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1171. Min Act: -0.0001

Data Index: 586113 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1111386 (C4 (Web Text))

Max Activating Token Index: 710