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

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

Neuron 150 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2989. Min Act: -0.0000

Data Index: 889950 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2815. Min Act: -0.0000

Data Index: 587962 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2671. Min Act: -0.0000

Data Index: 109392 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2414. Min Act: -0.0000

Data Index: 855493 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2196. Min Act: -0.0000

Data Index: 989370 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2153. Min Act: 0.0000

Data Index: 595902 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2131. Min Act: 0.0001

Data Index: 250772 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2165. Min Act: -0.0000

Data Index: 919696 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2087. Min Act: -0.0000

Data Index: 14583 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1188041 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1996. Min Act: -0.0000

Data Index: 35851 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1263670 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1924. Min Act: -0.0000

Data Index: 840574 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1923. Min Act: -0.0000

Data Index: 984930 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1170624 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1865. Min Act: -0.0000

Data Index: 540753 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1195095 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1831. Min Act: -0.0000

Data Index: 467726 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1961. Min Act: -0.0000

Data Index: 462132 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1900. Min Act: -0.0000

Data Index: 122060 (C4 (Web Text))

Max Activating Token Index: 339