Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4870 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0949. Min Act: -0.0003

Data Index: 388017 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0783. Min Act: -0.0002

Data Index: 985080 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0785. Min Act: -0.0003

Data Index: 910185 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0697. Min Act: -0.0003

Data Index: 331297 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0678. Min Act: -0.0003

Data Index: 1116472 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0657. Min Act: -0.0002

Data Index: 30440 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0598. Min Act: -0.0003

Data Index: 410176 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0665. Min Act: -0.0003

Data Index: 963885 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1303867 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0612. Min Act: -0.0003

Data Index: 814453 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1201991 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0640. Min Act: -0.0003

Data Index: 232259 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0599. Min Act: -0.0003

Data Index: 842794 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0610. Min Act: -0.0003

Data Index: 899521 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0609. Min Act: -0.0003

Data Index: 422260 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1247072 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1278032 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1218641 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0618. Min Act: -0.0003

Data Index: 515927 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0583. Min Act: -0.0003

Data Index: 376376 (C4 (Web Text))

Max Activating Token Index: 777