Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1734 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1975. Min Act: -0.0002

Data Index: 1389419 (Python Code)

Max Activating Token Index: 533

Text #1

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1614. Min Act: -0.0002

Data Index: 1581214 (Python Code)

Max Activating Token Index: 799

Text #2

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1664. Min Act: -0.0002

Data Index: 1633939 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1482. Min Act: -0.0002

Data Index: 1429411 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1500. Min Act: -0.0002

Data Index: 721930 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1458. Min Act: -0.0002

Data Index: 1643151 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1480. Min Act: -0.0002

Data Index: 1542703 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1479. Min Act: -0.0002

Data Index: 1655385 (Python Code)

Max Activating Token Index: 226

Text #8

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1470. Min Act: -0.0002

Data Index: 1584713 (Python Code)

Max Activating Token Index: 42

Text #9

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1444. Min Act: -0.0002

Data Index: 1449396 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1448. Min Act: -0.0002

Data Index: 1634933 (Python Code)

Max Activating Token Index: 750

Text #11

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1448. Min Act: -0.0002

Data Index: 1514736 (Python Code)

Max Activating Token Index: 239

Text #12

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1432. Min Act: -0.0002

Data Index: 1393822 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1509. Min Act: -0.0002

Data Index: 1636279 (Python Code)

Max Activating Token Index: 461

Text #14

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1550259 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1470. Min Act: -0.0002

Data Index: 1655062 (Python Code)

Max Activating Token Index: 950

Text #16

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1385. Min Act: -0.0002

Data Index: 1429905 (Python Code)

Max Activating Token Index: 982

Text #17

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1406. Min Act: -0.0002

Data Index: 1652086 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1435. Min Act: -0.0002

Data Index: 1548367 (Python Code)

Max Activating Token Index: 557

Text #19

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1432. Min Act: -0.0002

Data Index: 1562045 (Python Code)

Max Activating Token Index: 471