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

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

Neuron 193 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0606. Min Range: -4.0606

Max Act: 4.0606. Min Act: -0.0000

Data Index: 668392 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 4.0606. Min Range: -4.0606

Max Act: 3.5287. Min Act: -0.0000

Data Index: 943741 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 4.0606. Min Range: -4.0606

Max Act: 3.2581. Min Act: -0.0000

Data Index: 1342492 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 4.0606. Min Range: -4.0606

Max Act: 3.3476. Min Act: -0.0000

Data Index: 169485 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 4.0606. Min Range: -4.0606

Max Act: 3.5031. Min Act: -0.0000

Data Index: 551155 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 4.0606. Min Range: -4.0606

Max Act: 3.1231. Min Act: -0.0000

Data Index: 570037 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 4.0606. Min Range: -4.0606

Max Act: 3.1364. Min Act: -0.0000

Data Index: 1026647 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 4.0606. Min Range: -4.0606

Max Act: 2.9074. Min Act: -0.0000

Data Index: 121269 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 4.0606. Min Range: -4.0606

Max Act: 2.8939. Min Act: -0.0000

Data Index: 748186 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 4.0606. Min Range: -4.0606

Max Act: 3.0208. Min Act: -0.0000

Data Index: 901256 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 4.0606. Min Range: -4.0606

Max Act: 3.2904. Min Act: -0.0000

Data Index: 520618 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 4.0606. Min Range: -4.0606

Max Act: 2.9779. Min Act: -0.0000

Data Index: 837515 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 4.0606. Min Range: -4.0606

Max Act: 2.8538. Min Act: -0.0000

Data Index: 818954 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 4.0606. Min Range: -4.0606

Max Act: 3.1121. Min Act: -0.0000

Data Index: 859078 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 4.0606. Min Range: -4.0606

Max Act: 2.8381. Min Act: -0.0000

Data Index: 1231293 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 4.0606. Min Range: -4.0606

Max Act: 2.9277. Min Act: -0.0000

Data Index: 292305 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 4.0606. Min Range: -4.0606

Max Act: 2.9248. Min Act: -0.0000

Data Index: 34625 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 4.0606. Min Range: -4.0606

Max Act: 2.8876. Min Act: -0.0000

Data Index: 646851 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 4.0606. Min Range: -4.0606

Max Act: 2.8815. Min Act: -0.0000

Data Index: 588165 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 4.0606. Min Range: -4.0606

Max Act: 3.0235. Min Act: -0.0000

Data Index: 933227 (C4 (Web Text))

Max Activating Token Index: 144