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

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

Neuron 1927 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: 0.2928. Min Range: -0.2928

Max Act: 0.2837. Min Act: -0.0001

Data Index: 771424 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2928. Min Act: -0.0001

Data Index: 339148 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2789. Min Act: -0.0001

Data Index: 31171 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1052577 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2648. Min Act: -0.0001

Data Index: 1432051 (Python Code)

Max Activating Token Index: 900

Text #5

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2569. Min Act: -0.0001

Data Index: 899370 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2378. Min Act: -0.0001

Data Index: 1229731 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2358. Min Act: -0.0001

Data Index: 811797 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2379. Min Act: -0.0001

Data Index: 816668 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2410. Min Act: -0.0001

Data Index: 1645639 (Python Code)

Max Activating Token Index: 918

Text #10

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2220. Min Act: -0.0001

Data Index: 795825 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2092. Min Act: -0.0001

Data Index: 219804 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2352. Min Act: -0.0001

Data Index: 1249983 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2222. Min Act: -0.0001

Data Index: 507345 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2196. Min Act: -0.0001

Data Index: 137328 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2200. Min Act: -0.0001

Data Index: 422206 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2065. Min Act: -0.0001

Data Index: 685636 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2220. Min Act: -0.0001

Data Index: 711962 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2014. Min Act: -0.0001

Data Index: 69099 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2110. Min Act: -0.0001

Data Index: 30513 (C4 (Web Text))

Max Activating Token Index: 753