Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2333 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.8888. Min Range: -5.8888

Max Act: 5.7392. Min Act: -0.0000

Data Index: 574005 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 5.8888. Min Range: -5.8888

Max Act: 5.8888. Min Act: -0.0000

Data Index: 24647 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 5.8888. Min Range: -5.8888

Max Act: 5.0158. Min Act: -0.0000

Data Index: 1036953 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 5.8888. Min Range: -5.8888

Max Act: 5.2061. Min Act: -0.0000

Data Index: 885158 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.7950. Min Act: -0.0000

Data Index: 1616942 (Python Code)

Max Activating Token Index: 345

Text #5

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.7095. Min Act: -0.0000

Data Index: 342115 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 5.8888. Min Range: -5.8888

Max Act: 5.0079. Min Act: -0.0000

Data Index: 705382 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.8104. Min Act: -0.0000

Data Index: 1064014 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.6675. Min Act: -0.0000

Data Index: 1205449 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.5604. Min Act: -0.0000

Data Index: 421491 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.1258. Min Act: -0.0000

Data Index: 40218 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.4768. Min Act: -0.0000

Data Index: 1545729 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.4483. Min Act: -0.0000

Data Index: 1293458 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.4049. Min Act: -0.0000

Data Index: 483159 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.0855. Min Act: -0.0000

Data Index: 899019 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.5313. Min Act: -0.0000

Data Index: 771935 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.2710. Min Act: -0.0000

Data Index: 702857 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 5.8888. Min Range: -5.8888

Max Act: 3.2122. Min Act: -0.0000

Data Index: 678119 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 5.8888. Min Range: -5.8888

Max Act: 4.2276. Min Act: -0.0000

Data Index: 934909 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 5.8888. Min Range: -5.8888

Max Act: 3.7858. Min Act: -0.0000

Data Index: 1515429 (Python Code)

Max Activating Token Index: 268