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

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

Neuron 161 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: 0.0658. Min Range: -0.0658

Max Act: 0.0658. Min Act: -0.0002

Data Index: 919591 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0630. Min Act: -0.0002

Data Index: 129459 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1420548 (Python Code)

Max Activating Token Index: 293

Text #3

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0539. Min Act: -0.0002

Data Index: 541078 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0559. Min Act: -0.0002

Data Index: 678620 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0515. Min Act: -0.0002

Data Index: 642910 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0525. Min Act: -0.0002

Data Index: 504974 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0516. Min Act: -0.0002

Data Index: 942634 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1479241 (Python Code)

Max Activating Token Index: 569

Text #9

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1487292 (Python Code)

Max Activating Token Index: 843

Text #10

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1409895 (Python Code)

Max Activating Token Index: 958

Text #11

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0507. Min Act: -0.0002

Data Index: 19710 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0499. Min Act: -0.0002

Data Index: 356350 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1195291 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1382309 (Python Code)

Max Activating Token Index: 98

Text #15

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0485. Min Act: -0.0002

Data Index: 892540 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0515. Min Act: -0.0002

Data Index: 661005 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0484. Min Act: -0.0002

Data Index: 599105 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0488. Min Act: -0.0002

Data Index: 324172 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1501023 (Python Code)

Max Activating Token Index: 639