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

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

Neuron 2236 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1675. Min Act: -0.0002

Data Index: 1454508 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1568. Min Act: -0.0002

Data Index: 1414717 (Python Code)

Max Activating Token Index: 392

Text #2

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1555. Min Act: -0.0002

Data Index: 1636496 (Python Code)

Max Activating Token Index: 947

Text #3

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1458. Min Act: -0.0002

Data Index: 1415553 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1435. Min Act: -0.0002

Data Index: 1568569 (Python Code)

Max Activating Token Index: 763

Text #5

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1577948 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1363. Min Act: -0.0002

Data Index: 1485173 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1630822 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1304. Min Act: -0.0002

Data Index: 1539992 (Python Code)

Max Activating Token Index: 29

Text #9

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1622001 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1503150 (Python Code)

Max Activating Token Index: 485

Text #11

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1424383 (Python Code)

Max Activating Token Index: 151

Text #12

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1528452 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1415563 (Python Code)

Max Activating Token Index: 492

Text #14

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1256. Min Act: -0.0002

Data Index: 1530980 (Python Code)

Max Activating Token Index: 176

Text #15

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1461039 (Python Code)

Max Activating Token Index: 618

Text #16

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1491510 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1373527 (Python Code)

Max Activating Token Index: 83

Text #18

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1212. Min Act: -0.0002

Data Index: 1406895 (Python Code)

Max Activating Token Index: 220

Text #19

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1220. Min Act: -0.0002

Data Index: 1414145 (Python Code)

Max Activating Token Index: 805