Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 461 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.6846. Min Act: -0.0000

Data Index: 1093134 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.6863. Min Act: -0.0000

Data Index: 1214875 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.6426. Min Act: -0.0000

Data Index: 365175 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.5093. Min Act: -0.0000

Data Index: 1167003 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4232. Min Act: -0.0000

Data Index: 987827 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.2054. Min Act: -0.0000

Data Index: 959214 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.3183. Min Act: -0.0000

Data Index: 1248945 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.1694. Min Act: -0.0000

Data Index: 443341 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.1965. Min Act: -0.0000

Data Index: 249327 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1544674 (Python Code)

Max Activating Token Index: 1010

Text #10

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.1792. Min Act: -0.0000

Data Index: 585624 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1428113 (Python Code)

Max Activating Token Index: 737

Text #12

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.0542. Min Act: -0.0000

Data Index: 351734 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1207213 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.0411. Min Act: -0.0000

Data Index: 854041 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 1.6863. Min Range: -1.6863

Max Act: 0.9849. Min Act: -0.0000

Data Index: 1412381 (Python Code)

Max Activating Token Index: 887

Text #16

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1425988 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1400534 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 1.6863. Min Range: -1.6863

Max Act: 0.9058. Min Act: -0.0000

Data Index: 964063 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1568824 (Python Code)

Max Activating Token Index: 871