Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5166 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2487. Min Act: -0.0000

Data Index: 619111 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2301. Min Act: -0.0000

Data Index: 960348 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2044. Min Act: -0.0000

Data Index: 42051 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1036631 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2054. Min Act: -0.0000

Data Index: 536966 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1799. Min Act: -0.0000

Data Index: 3096 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1282525 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1921. Min Act: -0.0000

Data Index: 339026 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1860. Min Act: -0.0000

Data Index: 113135 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1708. Min Act: -0.0000

Data Index: 332213 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1823. Min Act: -0.0000

Data Index: 200650 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1773. Min Act: -0.0000

Data Index: 582315 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1657. Min Act: -0.0000

Data Index: 7844 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1714. Min Act: -0.0000

Data Index: 113279 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1631. Min Act: -0.0000

Data Index: 856357 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1622. Min Act: -0.0000

Data Index: 75212 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1454052 (Python Code)

Max Activating Token Index: 718

Text #17

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1609. Min Act: -0.0000

Data Index: 573549 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1185028 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1678. Min Act: -0.0000

Data Index: 972270 (C4 (Web Text))

Max Activating Token Index: 67