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

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

Neuron 1136 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3670. Min Range: -2.3670

Max Act: 2.3670. Min Act: -0.0000

Data Index: 1413548 (Python Code)

Max Activating Token Index: 335

Text #1

Max Range: 2.3670. Min Range: -2.3670

Max Act: 2.1532. Min Act: -0.0000

Data Index: 1458446 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 2.3670. Min Range: -2.3670

Max Act: 2.1883. Min Act: -0.0000

Data Index: 1093527 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 2.3670. Min Range: -2.3670

Max Act: 2.0035. Min Act: -0.0000

Data Index: 953873 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 2.3670. Min Range: -2.3670

Max Act: 2.0040. Min Act: -0.0000

Data Index: 1624286 (Python Code)

Max Activating Token Index: 104

Text #5

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.9643. Min Act: -0.0000

Data Index: 13505 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 2.3670. Min Range: -2.3670

Max Act: 2.1747. Min Act: -0.0000

Data Index: 97176 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 2.3670. Min Range: -2.3670

Max Act: 2.1662. Min Act: -0.0000

Data Index: 1487284 (Python Code)

Max Activating Token Index: 963

Text #8

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.9993. Min Act: -0.0000

Data Index: 1066519 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.9994. Min Act: -0.0000

Data Index: 550865 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.8638. Min Act: -0.0000

Data Index: 1108202 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.9622. Min Act: -0.0000

Data Index: 207868 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.9686. Min Act: -0.0000

Data Index: 5243 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 2.3670. Min Range: -2.3670

Max Act: 2.0508. Min Act: -0.0000

Data Index: 744509 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 2.3670. Min Range: -2.3670

Max Act: 2.1278. Min Act: -0.0000

Data Index: 1494657 (Python Code)

Max Activating Token Index: 737

Text #15

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.8747. Min Act: -0.0000

Data Index: 1513879 (Python Code)

Max Activating Token Index: 891

Text #16

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.7777. Min Act: -0.0000

Data Index: 1223185 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.6715. Min Act: -0.0000

Data Index: 1360001 (Python Code)

Max Activating Token Index: 755

Text #18

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.6934. Min Act: -0.0000

Data Index: 189752 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 2.3670. Min Range: -2.3670

Max Act: 1.8103. Min Act: -0.0000

Data Index: 352142 (C4 (Web Text))

Max Activating Token Index: 671