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

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

Neuron 702 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: 0.6678. Min Range: -0.6678

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1240390 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6207. Min Act: -0.0000

Data Index: 60584 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1183086 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6045. Min Act: -0.0000

Data Index: 534650 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6153. Min Act: -0.0000

Data Index: 486804 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6064. Min Act: -0.0000

Data Index: 347661 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5718. Min Act: -0.0000

Data Index: 845770 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5420. Min Act: -0.0000

Data Index: 36347 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1115049 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5227. Min Act: -0.0000

Data Index: 645877 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5607. Min Act: -0.0000

Data Index: 842794 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5324. Min Act: -0.0000

Data Index: 370137 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4868. Min Act: -0.0000

Data Index: 289332 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4989. Min Act: -0.0000

Data Index: 91394 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4997. Min Act: -0.0000

Data Index: 683511 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4942. Min Act: -0.0000

Data Index: 621447 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5345. Min Act: -0.0000

Data Index: 500103 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1236872 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4885. Min Act: -0.0000

Data Index: 481814 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4497. Min Act: -0.0000

Data Index: 892847 (C4 (Web Text))

Max Activating Token Index: 660