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

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

Neuron 6100 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1472. Min Act: -0.0002

Data Index: 429053 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1378184 (Python Code)

Max Activating Token Index: 383

Text #2

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1346. Min Act: -0.0002

Data Index: 1646736 (Python Code)

Max Activating Token Index: 906

Text #3

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1492680 (Python Code)

Max Activating Token Index: 728

Text #4

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1546656 (Python Code)

Max Activating Token Index: 572

Text #5

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1617186 (Python Code)

Max Activating Token Index: 222

Text #6

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1437469 (Python Code)

Max Activating Token Index: 594

Text #7

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1150. Min Act: -0.0002

Data Index: 1541672 (Python Code)

Max Activating Token Index: 234

Text #8

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1423830 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1367653 (Python Code)

Max Activating Token Index: 230

Text #10

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1579368 (Python Code)

Max Activating Token Index: 262

Text #11

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1451715 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1513986 (Python Code)

Max Activating Token Index: 921

Text #13

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1147. Min Act: -0.0002

Data Index: 1564830 (Python Code)

Max Activating Token Index: 645

Text #14

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1418852 (Python Code)

Max Activating Token Index: 584

Text #15

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1640785 (Python Code)

Max Activating Token Index: 857

Text #16

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1496859 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1528276 (Python Code)

Max Activating Token Index: 849

Text #18

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1121. Min Act: -0.0002

Data Index: 1395647 (Python Code)

Max Activating Token Index: 827

Text #19

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1157. Min Act: -0.0002

Data Index: 1363957 (Python Code)

Max Activating Token Index: 332