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

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

Neuron 2048 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2693. Min Act: -0.0000

Data Index: 320480 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2602. Min Act: -0.0000

Data Index: 762021 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1294237 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2209. Min Act: -0.0000

Data Index: 810179 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1100571 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2088. Min Act: -0.0000

Data Index: 218890 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2267. Min Act: -0.0000

Data Index: 945758 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2053. Min Act: -0.0000

Data Index: 993061 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2017. Min Act: -0.0000

Data Index: 921488 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1082901 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1272068 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2107. Min Act: -0.0000

Data Index: 121055 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1961. Min Act: -0.0000

Data Index: 871962 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1712. Min Act: -0.0000

Data Index: 369416 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1016253 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1751. Min Act: -0.0000

Data Index: 18215 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1745. Min Act: -0.0000

Data Index: 878361 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1736. Min Act: -0.0000

Data Index: 681471 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1070342 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1701. Min Act: -0.0000

Data Index: 394298 (C4 (Web Text))

Max Activating Token Index: 121