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

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

Neuron 3109 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2532. Min Range: -2.2532

Max Act: 2.2532. Min Act: -0.0001

Data Index: 2338 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 2.2532. Min Range: -2.2532

Max Act: 2.1062. Min Act: -0.0001

Data Index: 239956 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 2.2532. Min Range: -2.2532

Max Act: 2.0780. Min Act: -0.0000

Data Index: 827620 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 2.2532. Min Range: -2.2532

Max Act: 2.0112. Min Act: -0.0000

Data Index: 622211 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 2.2532. Min Range: -2.2532

Max Act: 2.0376. Min Act: -0.0001

Data Index: 613524 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.8688. Min Act: -0.0000

Data Index: 393367 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.9200. Min Act: -0.0000

Data Index: 1047814 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.9767. Min Act: -0.0001

Data Index: 1071086 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.9013. Min Act: -0.0000

Data Index: 762329 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.7645. Min Act: -0.0000

Data Index: 952280 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.8100. Min Act: -0.0000

Data Index: 1323485 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.7774. Min Act: -0.0000

Data Index: 446187 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.7983. Min Act: -0.0000

Data Index: 534129 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.8798. Min Act: -0.0001

Data Index: 989290 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.9073. Min Act: -0.0001

Data Index: 1352061 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.8247. Min Act: -0.0001

Data Index: 679433 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.7201. Min Act: -0.0000

Data Index: 898353 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.7432. Min Act: -0.0001

Data Index: 872006 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.8118. Min Act: -0.0001

Data Index: 273828 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 2.2532. Min Range: -2.2532

Max Act: 1.7245. Min Act: -0.0001

Data Index: 886673 (C4 (Web Text))

Max Activating Token Index: 44