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

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

Neuron 2584 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: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1088638 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0848. Min Act: -0.0001

Data Index: 252785 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0838. Min Act: -0.0001

Data Index: 644099 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0800. Min Act: -0.0001

Data Index: 365294 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0682. Min Act: -0.0001

Data Index: 376439 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0660. Min Act: -0.0001

Data Index: 309848 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0657. Min Act: -0.0001

Data Index: 449618 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0664. Min Act: -0.0001

Data Index: 196975 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0637. Min Act: -0.0001

Data Index: 599071 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0612. Min Act: -0.0001

Data Index: 995800 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0569. Min Act: -0.0001

Data Index: 370492 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1098260 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0658. Min Act: -0.0001

Data Index: 167770 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0609. Min Act: -0.0001

Data Index: 820730 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0573. Min Act: -0.0001

Data Index: 931461 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0559. Min Act: -0.0001

Data Index: 276209 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0597. Min Act: -0.0001

Data Index: 510021 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0549. Min Act: -0.0001

Data Index: 69667 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0577. Min Act: -0.0001

Data Index: 969006 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0571. Min Act: -0.0001

Data Index: 882799 (C4 (Web Text))

Max Activating Token Index: 21