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

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

Neuron 3234 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: 0.4347. Min Range: -0.4347

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1476405 (Python Code)

Max Activating Token Index: 701

Text #1

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1503238 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1471304 (Python Code)

Max Activating Token Index: 990

Text #3

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1623656 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1652731 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1457222 (Python Code)

Max Activating Token Index: 886

Text #6

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1630683 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1472889 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1626961 (Python Code)

Max Activating Token Index: 757

Text #9

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1605967 (Python Code)

Max Activating Token Index: 852

Text #10

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1364753 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3180. Min Act: -0.0000

Data Index: 650670 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2728. Min Act: -0.0000

Data Index: 924826 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2996. Min Act: -0.0000

Data Index: 109197 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1397400 (Python Code)

Max Activating Token Index: 943

Text #15

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1640844 (Python Code)

Max Activating Token Index: 1011

Text #16

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2929. Min Act: -0.0001

Data Index: 482937 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2880. Min Act: -0.0000

Data Index: 194760 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1468415 (Python Code)

Max Activating Token Index: 965

Text #19

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2604. Min Act: -0.0000

Data Index: 868155 (C4 (Web Text))

Max Activating Token Index: 725