Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2076 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0762. Min Act: -0.0001

Data Index: 837051 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0720. Min Act: -0.0001

Data Index: 194151 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0650. Min Act: -0.0001

Data Index: 28178 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1302032 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1129136 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0591. Min Act: -0.0001

Data Index: 752414 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0657. Min Act: -0.0001

Data Index: 1213495 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0669. Min Act: -0.0001

Data Index: 804612 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0660. Min Act: -0.0001

Data Index: 501605 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0635. Min Act: -0.0001

Data Index: 828589 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0634. Min Act: -0.0001

Data Index: 531034 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0600. Min Act: -0.0001

Data Index: 350956 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0612. Min Act: -0.0001

Data Index: 578381 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0665. Min Act: -0.0001

Data Index: 745808 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0608. Min Act: -0.0001

Data Index: 788363 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0528. Min Act: -0.0001

Data Index: 925239 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0561. Min Act: -0.0001

Data Index: 850354 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1309492 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0582. Min Act: -0.0001

Data Index: 109296 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0563. Min Act: -0.0001

Data Index: 352912 (C4 (Web Text))

Max Activating Token Index: 635