Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4048 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0661. Min Act: -0.0003

Data Index: 951950 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0674. Min Act: -0.0003

Data Index: 891699 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0003

Data Index: 1350258 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0658. Min Act: -0.0003

Data Index: 865131 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1127497 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0596. Min Act: -0.0003

Data Index: 36205 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1252181 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1102006 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1312670 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0613. Min Act: -0.0003

Data Index: 770164 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0575. Min Act: -0.0003

Data Index: 640575 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0563. Min Act: -0.0003

Data Index: 31680 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0607. Min Act: -0.0003

Data Index: 98516 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0607. Min Act: -0.0003

Data Index: 54505 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1045913 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1296841 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0554. Min Act: -0.0003

Data Index: 834902 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1058953 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0567. Min Act: -0.0003

Data Index: 149409 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1146902 (C4 (Web Text))

Max Activating Token Index: 1009