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

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

Neuron 3093 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5602. Min Act: -0.0001

Data Index: 727859 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5849. Min Act: -0.0001

Data Index: 58832 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5293. Min Act: -0.0001

Data Index: 116473 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5396. Min Act: -0.0001

Data Index: 1275998 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5359. Min Act: -0.0001

Data Index: 1048936 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5141. Min Act: -0.0001

Data Index: 249196 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4933. Min Act: -0.0001

Data Index: 502418 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4761. Min Act: -0.0001

Data Index: 561150 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1206756 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4832. Min Act: -0.0001

Data Index: 596163 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4636. Min Act: -0.0001

Data Index: 122512 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4597. Min Act: -0.0001

Data Index: 233696 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4601. Min Act: -0.0001

Data Index: 635035 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4253. Min Act: -0.0001

Data Index: 166967 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4647. Min Act: -0.0001

Data Index: 778927 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4058. Min Act: -0.0001

Data Index: 776485 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4384. Min Act: -0.0001

Data Index: 1275387 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4359. Min Act: -0.0001

Data Index: 1048919 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4367. Min Act: -0.0001

Data Index: 10436 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4317. Min Act: -0.0001

Data Index: 325657 (C4 (Web Text))

Max Activating Token Index: 789