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

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

Neuron 42 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3487. Min Range: -2.3487

Max Act: 2.3487. Min Act: -0.0000

Data Index: 886529 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 2.3487. Min Range: -2.3487

Max Act: 2.1330. Min Act: -0.0000

Data Index: 1302956 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 2.3487. Min Range: -2.3487

Max Act: 2.1782. Min Act: -0.0000

Data Index: 165279 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 2.3487. Min Range: -2.3487

Max Act: 2.0328. Min Act: -0.0000

Data Index: 932951 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 2.3487. Min Range: -2.3487

Max Act: 2.0027. Min Act: -0.0000

Data Index: 678416 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 2.3487. Min Range: -2.3487

Max Act: 2.1055. Min Act: -0.0000

Data Index: 77495 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.9995. Min Act: -0.0000

Data Index: 782985 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 2.3487. Min Range: -2.3487

Max Act: 2.1016. Min Act: -0.0000

Data Index: 104690 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 2.3487. Min Range: -2.3487

Max Act: 2.0855. Min Act: -0.0000

Data Index: 24054 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.9503. Min Act: -0.0000

Data Index: 590447 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 2.3487. Min Range: -2.3487

Max Act: 2.0624. Min Act: -0.0001

Data Index: 953020 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.8122. Min Act: -0.0001

Data Index: 495213 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.8697. Min Act: -0.0001

Data Index: 1351405 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.7025. Min Act: -0.0000

Data Index: 1331958 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.8520. Min Act: -0.0000

Data Index: 282299 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.8475. Min Act: -0.0000

Data Index: 535433 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.9766. Min Act: -0.0000

Data Index: 1302275 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.7464. Min Act: -0.0001

Data Index: 1318425 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.8263. Min Act: -0.0000

Data Index: 797201 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 2.3487. Min Range: -2.3487

Max Act: 1.8289. Min Act: -0.0001

Data Index: 23758 (C4 (Web Text))

Max Activating Token Index: 831