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

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

Neuron 1238 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3289. Min Act: -0.0000

Data Index: 382634 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2375. Min Act: -0.0000

Data Index: 691979 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2328. Min Act: -0.0000

Data Index: 811703 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1057456 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2162. Min Act: -0.0000

Data Index: 817142 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1952. Min Act: -0.0000

Data Index: 261290 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1835. Min Act: -0.0000

Data Index: 309925 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1821. Min Act: -0.0000

Data Index: 194291 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1037146 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1848. Min Act: 0.0000

Data Index: 931174 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1740. Min Act: -0.0000

Data Index: 246308 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1718. Min Act: -0.0000

Data Index: 119700 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1666. Min Act: -0.0000

Data Index: 984077 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1684. Min Act: 0.0000

Data Index: 1300160 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1652. Min Act: 0.0000

Data Index: 881789 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1159838 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1523. Min Act: 0.0000

Data Index: 449326 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1514. Min Act: 0.0000

Data Index: 133183 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1035814 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1467. Min Act: -0.0000

Data Index: 581835 (C4 (Web Text))

Max Activating Token Index: 381