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

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

Neuron 4431 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: 0.7699. Min Range: -0.7699

Max Act: 0.7699. Min Act: 0.0000

Data Index: 1225876 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.6281. Min Act: 0.0000

Data Index: 737153 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1547096 (Python Code)

Max Activating Token Index: 931

Text #3

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4915. Min Act: -0.0000

Data Index: 160982 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4347. Min Act: 0.0000

Data Index: 140254 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4015. Min Act: -0.0000

Data Index: 458686 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4017. Min Act: -0.0000

Data Index: 725917 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1140932 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1224244 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3957. Min Act: -0.0000

Data Index: 879115 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1438339 (Python Code)

Max Activating Token Index: 302

Text #11

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1571484 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3357. Min Act: 0.0000

Data Index: 1533707 (Python Code)

Max Activating Token Index: 518

Text #13

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3351. Min Act: 0.0001

Data Index: 671628 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3222. Min Act: 0.0001

Data Index: 556788 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3229. Min Act: 0.0000

Data Index: 210665 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1580517 (Python Code)

Max Activating Token Index: 655

Text #17

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1273128 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.2994. Min Act: 0.0000

Data Index: 1633540 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1590021 (Python Code)

Max Activating Token Index: 825