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

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

Neuron 904 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.2088. Min Act: -0.0000

Data Index: 379764 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1214393 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1291115 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.2038. Min Act: -0.0000

Data Index: 823130 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1725. Min Act: -0.0000

Data Index: 799841 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1665. Min Act: -0.0000

Data Index: 952860 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1706. Min Act: -0.0000

Data Index: 133625 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1675. Min Act: -0.0000

Data Index: 925250 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1663. Min Act: -0.0000

Data Index: 249781 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1311301 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1294017 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1029101 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1595. Min Act: -0.0001

Data Index: 661939 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1578. Min Act: -0.0001

Data Index: 567698 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1544. Min Act: -0.0000

Data Index: 841947 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1550. Min Act: -0.0000

Data Index: 15982 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1596. Min Act: -0.0000

Data Index: 542236 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1650. Min Act: -0.0001

Data Index: 756577 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1248839 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1625. Min Act: -0.0001

Data Index: 798866 (C4 (Web Text))

Max Activating Token Index: 824