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

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

Neuron 1358 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: 0.1986. Min Range: -0.1986

Max Act: 0.1986. Min Act: -0.0002

Data Index: 28745 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1893. Min Act: -0.0002

Data Index: 998898 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1883. Min Act: -0.0002

Data Index: 452825 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1820. Min Act: -0.0001

Data Index: 154565 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1875. Min Act: -0.0002

Data Index: 1233956 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1830. Min Act: -0.0002

Data Index: 1216419 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1799. Min Act: -0.0002

Data Index: 1208049 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1698. Min Act: -0.0001

Data Index: 73295 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1639. Min Act: -0.0002

Data Index: 562764 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1703. Min Act: -0.0002

Data Index: 850169 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1678. Min Act: -0.0002

Data Index: 60118 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1629. Min Act: -0.0002

Data Index: 34744 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1618. Min Act: -0.0002

Data Index: 436663 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1639. Min Act: -0.0002

Data Index: 6039 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1470. Min Act: -0.0002

Data Index: 300592 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1602. Min Act: -0.0002

Data Index: 322675 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1611. Min Act: -0.0002

Data Index: 939790 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1588. Min Act: -0.0002

Data Index: 899058 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1517. Min Act: -0.0002

Data Index: 1295068 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1580. Min Act: -0.0002

Data Index: 118347 (C4 (Web Text))

Max Activating Token Index: 536