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

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

Neuron 13 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1772. Min Act: -0.0001

Data Index: 298920 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1831. Min Act: -0.0001

Data Index: 184860 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1723. Min Act: -0.0001

Data Index: 1295427 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1349412 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1663. Min Act: -0.0001

Data Index: 1005038 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1308976 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1178022 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1576. Min Act: -0.0001

Data Index: 307641 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1572. Min Act: -0.0001

Data Index: 831282 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1155036 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1609. Min Act: -0.0001

Data Index: 928210 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1668. Min Act: -0.0001

Data Index: 872881 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1216716 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1657. Min Act: -0.0001

Data Index: 366573 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1595. Min Act: -0.0001

Data Index: 676732 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1644. Min Act: -0.0001

Data Index: 315819 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1209024 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1011282 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1227955 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1578. Min Act: -0.0001

Data Index: 639808 (C4 (Web Text))

Max Activating Token Index: 831