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

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

Neuron 2646 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1281084 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1817. Min Act: -0.0000

Data Index: 537093 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1866. Min Act: -0.0000

Data Index: 334138 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1432478 (Python Code)

Max Activating Token Index: 319

Text #4

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1979. Min Act: -0.0000

Data Index: 363406 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1218797 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1816. Min Act: -0.0000

Data Index: 942530 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1788. Min Act: -0.0000

Data Index: 168774 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1409116 (Python Code)

Max Activating Token Index: 243

Text #9

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1623. Min Act: -0.0000

Data Index: 342092 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1702. Min Act: -0.0000

Data Index: 502171 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1597. Min Act: -0.0000

Data Index: 156060 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1202333 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1287378 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1240246 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1465. Min Act: -0.0000

Data Index: 869937 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1651207 (Python Code)

Max Activating Token Index: 412

Text #17

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1414. Min Act: -0.0000

Data Index: 367668 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1083466 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1393. Min Act: -0.0000

Data Index: 818823 (C4 (Web Text))

Max Activating Token Index: 412