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

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

Neuron 5446 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.7760. Min Act: -0.0000

Data Index: 59361 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.4874. Min Act: -0.0000

Data Index: 1330394 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.6146. Min Act: -0.0000

Data Index: 477872 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.4232. Min Act: -0.0000

Data Index: 1017637 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.2293. Min Act: -0.0000

Data Index: 741250 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.3074. Min Act: -0.0000

Data Index: 950848 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.0570. Min Act: -0.0000

Data Index: 48315 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.6886. Min Act: -0.0000

Data Index: 415997 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.4880. Min Act: -0.0000

Data Index: 827160 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.4228. Min Act: -0.0000

Data Index: 1139210 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.3213. Min Act: -0.0000

Data Index: 22629 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.3008. Min Act: -0.0000

Data Index: 561043 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.1852. Min Act: -0.0000

Data Index: 442916 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.2458. Min Act: -0.0000

Data Index: 260598 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.2125. Min Act: 0.0000

Data Index: 1320322 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.2015. Min Act: -0.0000

Data Index: 322445 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.1906. Min Act: -0.0000

Data Index: 317709 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.2447. Min Act: -0.0000

Data Index: 260734 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.1437. Min Act: -0.0000

Data Index: 103359 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.1006. Min Act: -0.0000

Data Index: 183412 (C4 (Web Text))

Max Activating Token Index: 47