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

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

Neuron 2901 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: 4.8871. Min Range: -4.8871

Max Act: 4.8871. Min Act: -0.0000

Data Index: 1601630 (Python Code)

Max Activating Token Index: 748

Text #1

Max Range: 4.8871. Min Range: -4.8871

Max Act: 4.3254. Min Act: -0.0000

Data Index: 1585607 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 4.8871. Min Range: -4.8871

Max Act: 4.4222. Min Act: -0.0000

Data Index: 1413683 (Python Code)

Max Activating Token Index: 1019

Text #3

Max Range: 4.8871. Min Range: -4.8871

Max Act: 4.3603. Min Act: -0.0000

Data Index: 1648190 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 4.8871. Min Range: -4.8871

Max Act: 4.2621. Min Act: -0.0000

Data Index: 1375002 (Python Code)

Max Activating Token Index: 780

Text #5

Max Range: 4.8871. Min Range: -4.8871

Max Act: 4.0954. Min Act: -0.0000

Data Index: 1386770 (Python Code)

Max Activating Token Index: 164

Text #6

Max Range: 4.8871. Min Range: -4.8871

Max Act: 4.8147. Min Act: -0.0000

Data Index: 1540982 (Python Code)

Max Activating Token Index: 725

Text #7

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.8900. Min Act: -0.0000

Data Index: 1611310 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.8288. Min Act: -0.0000

Data Index: 637478 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.9071. Min Act: -0.0000

Data Index: 1383163 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.5202. Min Act: -0.0000

Data Index: 921969 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 4.8871. Min Range: -4.8871

Max Act: 4.2625. Min Act: -0.0000

Data Index: 1589437 (Python Code)

Max Activating Token Index: 882

Text #12

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.7755. Min Act: -0.0000

Data Index: 676416 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.5931. Min Act: -0.0000

Data Index: 1413838 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.5334. Min Act: -0.0000

Data Index: 1443476 (Python Code)

Max Activating Token Index: 971

Text #15

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.6900. Min Act: -0.0000

Data Index: 1525801 (Python Code)

Max Activating Token Index: 964

Text #16

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.8657. Min Act: -0.0000

Data Index: 1364291 (Python Code)

Max Activating Token Index: 184

Text #17

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.3215. Min Act: -0.0000

Data Index: 1533830 (Python Code)

Max Activating Token Index: 133

Text #18

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.2616. Min Act: -0.0000

Data Index: 1491599 (Python Code)

Max Activating Token Index: 883

Text #19

Max Range: 4.8871. Min Range: -4.8871

Max Act: 3.1841. Min Act: -0.0000

Data Index: 1438159 (Python Code)

Max Activating Token Index: 904