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

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

Neuron 5850 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.6368. Min Act: -0.0000

Data Index: 585122 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.6167. Min Act: -0.0000

Data Index: 764452 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.3401. Min Act: -0.0001

Data Index: 1332272 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.2919. Min Act: -0.0001

Data Index: 531400 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.1566. Min Act: -0.0000

Data Index: 905527 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.1857. Min Act: -0.0000

Data Index: 1395822 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.1436. Min Act: -0.0000

Data Index: 706508 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.0967. Min Act: -0.0001

Data Index: 129756 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.0713. Min Act: -0.0001

Data Index: 512852 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1184363 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.1012. Min Act: -0.0000

Data Index: 212818 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.0710. Min Act: -0.0000

Data Index: 194964 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.6368. Min Range: -1.6368

Max Act: 0.9982. Min Act: -0.0000

Data Index: 258111 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 1.6368. Min Range: -1.6368

Max Act: 0.9892. Min Act: -0.0000

Data Index: 81275 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 1.6368. Min Range: -1.6368

Max Act: 0.9746. Min Act: -0.0000

Data Index: 165056 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 1.6368. Min Range: -1.6368

Max Act: 0.9818. Min Act: -0.0000

Data Index: 988965 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 1.6368. Min Range: -1.6368

Max Act: 0.9626. Min Act: -0.0000

Data Index: 102986 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.6368. Min Range: -1.6368

Max Act: 0.8972. Min Act: -0.0000

Data Index: 359063 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.6368. Min Range: -1.6368

Max Act: 0.9643. Min Act: -0.0000

Data Index: 14247 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 1.6368. Min Range: -1.6368

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1084349 (C4 (Web Text))

Max Activating Token Index: 851