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

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

Neuron 229 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: 1.8460. Min Range: -1.8460

Max Act: 1.8460. Min Act: -0.0000

Data Index: 1613356 (Python Code)

Max Activating Token Index: 931

Text #1

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.4460. Min Act: -0.0000

Data Index: 1426470 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.3443. Min Act: -0.0000

Data Index: 971444 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.5011. Min Act: -0.0000

Data Index: 1515051 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.3875. Min Act: -0.0000

Data Index: 1408379 (Python Code)

Max Activating Token Index: 364

Text #5

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.2472. Min Act: -0.0000

Data Index: 1433565 (Python Code)

Max Activating Token Index: 789

Text #6

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1521921 (Python Code)

Max Activating Token Index: 731

Text #7

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.2223. Min Act: -0.0000

Data Index: 358719 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1055164 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1537722 (Python Code)

Max Activating Token Index: 595

Text #10

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1599462 (Python Code)

Max Activating Token Index: 650

Text #11

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.1878. Min Act: -0.0000

Data Index: 1378521 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1523925 (Python Code)

Max Activating Token Index: 468

Text #13

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1625150 (Python Code)

Max Activating Token Index: 95

Text #14

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1596922 (Python Code)

Max Activating Token Index: 544

Text #15

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1394970 (Python Code)

Max Activating Token Index: 975

Text #16

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.0901. Min Act: -0.0000

Data Index: 1501013 (Python Code)

Max Activating Token Index: 921

Text #17

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.1050. Min Act: -0.0000

Data Index: 425574 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1309142 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.1599. Min Act: -0.0000

Data Index: 1451203 (Python Code)

Max Activating Token Index: 925