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

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

Neuron 3158 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: 0.3799. Min Range: -0.3799

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1643312 (Python Code)

Max Activating Token Index: 855

Text #1

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3660. Min Act: 0.0001

Data Index: 1637513 (Python Code)

Max Activating Token Index: 326

Text #2

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3608. Min Act: -0.0000

Data Index: 941405 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1614500 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3201. Min Act: -0.0000

Data Index: 126979 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3147. Min Act: -0.0000

Data Index: 402184 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1587906 (Python Code)

Max Activating Token Index: 974

Text #7

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3179. Min Act: -0.0000

Data Index: 468646 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1369325 (Python Code)

Max Activating Token Index: 632

Text #9

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2961. Min Act: 0.0000

Data Index: 905851 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2836. Min Act: 0.0000

Data Index: 1517667 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1411711 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1443464 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2904. Min Act: -0.0000

Data Index: 404836 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1055917 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2851. Min Act: 0.0001

Data Index: 1362552 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1442114 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2745. Min Act: -0.0000

Data Index: 454379 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2806. Min Act: 0.0000

Data Index: 1398681 (Python Code)

Max Activating Token Index: 432

Text #19

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1244442 (C4 (Web Text))

Max Activating Token Index: 807