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

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

Neuron 5576 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0417. Min Range: -3.0417

Max Act: 3.0417. Min Act: -0.0000

Data Index: 1250535 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.8556. Min Act: -0.0000

Data Index: 195294 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.6667. Min Act: -0.0000

Data Index: 323160 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.4200. Min Act: -0.0000

Data Index: 507984 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.5422. Min Act: -0.0000

Data Index: 297427 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.4221. Min Act: -0.0000

Data Index: 51696 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.5839. Min Act: -0.0000

Data Index: 908293 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.4948. Min Act: -0.0001

Data Index: 89107 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.5691. Min Act: -0.0000

Data Index: 1230708 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.3624. Min Act: -0.0000

Data Index: 587618 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.4064. Min Act: -0.0001

Data Index: 1249220 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 3.0417. Min Range: -3.0417

Max Act: 1.8380. Min Act: -0.0000

Data Index: 1017611 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.1504. Min Act: -0.0001

Data Index: 1250567 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.4765. Min Act: -0.0000

Data Index: 84910 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.2309. Min Act: -0.0000

Data Index: 87192 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.2470. Min Act: -0.0000

Data Index: 305386 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.3361. Min Act: -0.0001

Data Index: 1129626 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.3554. Min Act: -0.0000

Data Index: 612177 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.4489. Min Act: -0.0000

Data Index: 1320437 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 3.0417. Min Range: -3.0417

Max Act: 2.2046. Min Act: -0.0000

Data Index: 52085 (C4 (Web Text))

Max Activating Token Index: 962