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

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

Neuron 2741 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: 0.2865. Min Range: -0.2865

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1298397 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1201143 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1123655 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2348. Min Act: -0.0000

Data Index: 128056 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2290. Min Act: -0.0000

Data Index: 921088 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2357. Min Act: -0.0000

Data Index: 108423 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1653193 (Python Code)

Max Activating Token Index: 462

Text #7

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1233070 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1007937 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2252. Min Act: -0.0001

Data Index: 686917 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2015. Min Act: -0.0000

Data Index: 933837 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1642703 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1288325 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2016. Min Act: -0.0000

Data Index: 365302 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1345135 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1011375 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1779. Min Act: -0.0001

Data Index: 581762 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1957. Min Act: -0.0000

Data Index: 998130 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1283303 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1950. Min Act: -0.0001

Data Index: 241613 (C4 (Web Text))

Max Activating Token Index: 561