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

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

Neuron 4293 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1481. Min Act: -0.0002

Data Index: 1427518 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1649098 (Python Code)

Max Activating Token Index: 227

Text #2

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1431. Min Act: -0.0002

Data Index: 1478084 (Python Code)

Max Activating Token Index: 723

Text #3

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1460. Min Act: -0.0002

Data Index: 1485794 (Python Code)

Max Activating Token Index: 964

Text #4

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1314. Min Act: -0.0002

Data Index: 1388985 (Python Code)

Max Activating Token Index: 425

Text #5

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1307. Min Act: -0.0002

Data Index: 1363799 (Python Code)

Max Activating Token Index: 225

Text #6

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1366. Min Act: -0.0002

Data Index: 1597234 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1562557 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1275. Min Act: -0.0002

Data Index: 1439311 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1506265 (Python Code)

Max Activating Token Index: 705

Text #10

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1167. Min Act: -0.0002

Data Index: 1599897 (Python Code)

Max Activating Token Index: 862

Text #11

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1279. Min Act: -0.0002

Data Index: 1630756 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1204. Min Act: -0.0002

Data Index: 1583839 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1224. Min Act: -0.0002

Data Index: 1428252 (Python Code)

Max Activating Token Index: 993

Text #14

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1535368 (Python Code)

Max Activating Token Index: 571

Text #15

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1559837 (Python Code)

Max Activating Token Index: 615

Text #16

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1382681 (Python Code)

Max Activating Token Index: 990

Text #17

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1553031 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1482284 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1529940 (Python Code)

Max Activating Token Index: 217