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

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

Neuron 3581 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2727. Min Act: -0.0000

Data Index: 115989 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2443. Min Act: -0.0000

Data Index: 415858 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2607. Min Act: -0.0000

Data Index: 925874 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1133391 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2183. Min Act: -0.0000

Data Index: 590637 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1307694 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1017831 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1958. Min Act: -0.0000

Data Index: 72303 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2144. Min Act: -0.0000

Data Index: 205590 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1929. Min Act: -0.0000

Data Index: 696055 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1093420 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1284125 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1077042 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1254334 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1832. Min Act: -0.0001

Data Index: 719121 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1069726 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1857. Min Act: -0.0000

Data Index: 264447 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1160633 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1731. Min Act: -0.0000

Data Index: 656942 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1893. Min Act: -0.0000

Data Index: 99164 (C4 (Web Text))

Max Activating Token Index: 843