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

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

Neuron 1705 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.6575. Min Act: -0.0000

Data Index: 1499508 (Python Code)

Max Activating Token Index: 910

Text #1

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.2807. Min Act: -0.0000

Data Index: 187173 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.2993. Min Act: -0.0000

Data Index: 234900 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.3035. Min Act: -0.0000

Data Index: 1475941 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.2323. Min Act: -0.0001

Data Index: 989385 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.2299. Min Act: -0.0001

Data Index: 1314589 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.1912. Min Act: -0.0000

Data Index: 91705 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.1527. Min Act: -0.0000

Data Index: 1135822 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.2424. Min Act: -0.0001

Data Index: 75095 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.1677. Min Act: -0.0001

Data Index: 1643268 (Python Code)

Max Activating Token Index: 518

Text #10

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.1678. Min Act: -0.0000

Data Index: 52861 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.2445. Min Act: -0.0001

Data Index: 801670 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.1495. Min Act: -0.0001

Data Index: 1631001 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.1608. Min Act: -0.0001

Data Index: 1503855 (Python Code)

Max Activating Token Index: 280

Text #14

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.1660. Min Act: -0.0001

Data Index: 732306 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.1012. Min Act: -0.0001

Data Index: 128025 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.0606. Min Act: -0.0000

Data Index: 789639 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.0126. Min Act: -0.0001

Data Index: 174080 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.0106. Min Act: -0.0001

Data Index: 195524 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.6575. Min Range: -1.6575

Max Act: 1.0739. Min Act: -0.0001

Data Index: 1254810 (C4 (Web Text))

Max Activating Token Index: 256