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

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

Neuron 3824 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4409. Min Range: -1.4409

Max Act: 1.4409. Min Act: -0.0000

Data Index: 683953 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.4409. Min Range: -1.4409

Max Act: 1.4160. Min Act: -0.0000

Data Index: 317110 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 1.4409. Min Range: -1.4409

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1318202 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 1.4409. Min Range: -1.4409

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1170694 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1032832 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.9607. Min Act: -0.0000

Data Index: 1206334 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.9525. Min Act: -0.0000

Data Index: 711052 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1212380 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1089531 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1135311 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.9574. Min Act: -0.0000

Data Index: 886452 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1209398 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.9072. Min Act: -0.0000

Data Index: 864496 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.8892. Min Act: -0.0000

Data Index: 900060 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.8968. Min Act: -0.0000

Data Index: 169360 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.8869. Min Act: -0.0000

Data Index: 516605 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.8909. Min Act: -0.0000

Data Index: 551965 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.8762. Min Act: -0.0000

Data Index: 124999 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.8321. Min Act: -0.0000

Data Index: 364691 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.4409. Min Range: -1.4409

Max Act: 0.9007. Min Act: -0.0000

Data Index: 603269 (C4 (Web Text))

Max Activating Token Index: 304