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

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

Neuron 2353 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1961. Min Act: -0.0001

Data Index: 445517 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1939. Min Act: -0.0001

Data Index: 112963 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1650. Min Act: -0.0001

Data Index: 390197 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1690. Min Act: -0.0001

Data Index: 514041 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1684. Min Act: -0.0001

Data Index: 7528 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1571. Min Act: -0.0001

Data Index: 670358 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1586. Min Act: -0.0001

Data Index: 943974 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1573. Min Act: -0.0001

Data Index: 106245 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1626. Min Act: -0.0001

Data Index: 163858 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1572. Min Act: -0.0001

Data Index: 484645 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1511. Min Act: -0.0001

Data Index: 947867 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1546. Min Act: -0.0001

Data Index: 610081 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1016746 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1067915 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1602. Min Act: -0.0001

Data Index: 316736 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1583. Min Act: -0.0001

Data Index: 751376 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1471. Min Act: -0.0001

Data Index: 29728 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1526. Min Act: -0.0001

Data Index: 151347 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1229762 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1192687 (C4 (Web Text))

Max Activating Token Index: 38