Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3918 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4787. Min Act: -0.0001

Data Index: 304056 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4543. Min Act: -0.0002

Data Index: 386474 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4832. Min Act: -0.0001

Data Index: 145618 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4277. Min Act: -0.0002

Data Index: 978019 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4280. Min Act: -0.0001

Data Index: 128903 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4162. Min Act: -0.0001

Data Index: 1295257 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4014. Min Act: -0.0002

Data Index: 606503 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3943. Min Act: -0.0001

Data Index: 754291 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3896. Min Act: -0.0001

Data Index: 916931 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3828. Min Act: -0.0001

Data Index: 771312 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3964. Min Act: -0.0002

Data Index: 546176 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4048. Min Act: -0.0001

Data Index: 982475 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3905. Min Act: -0.0001

Data Index: 378037 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3909. Min Act: -0.0001

Data Index: 83922 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3905. Min Act: -0.0001

Data Index: 671277 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3768. Min Act: -0.0001

Data Index: 902744 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3701. Min Act: -0.0002

Data Index: 118120 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3709. Min Act: -0.0002

Data Index: 356941 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3943. Min Act: -0.0001

Data Index: 599884 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3807. Min Act: -0.0001

Data Index: 1228328 (C4 (Web Text))

Max Activating Token Index: 823