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

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

Neuron 2603 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.4001. Min Act: -0.0001

Data Index: 256848 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.4715. Min Act: -0.0001

Data Index: 618712 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.4138. Min Act: -0.0001

Data Index: 969890 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.2809. Min Act: -0.0000

Data Index: 717201 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.2684. Min Act: -0.0001

Data Index: 974945 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.1785. Min Act: -0.0001

Data Index: 1146101 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.1831. Min Act: -0.0001

Data Index: 696000 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.2104. Min Act: -0.0001

Data Index: 855511 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.1175. Min Act: -0.0001

Data Index: 535658 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.1037. Min Act: -0.0001

Data Index: 1332409 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.0770. Min Act: -0.0001

Data Index: 1071958 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.0240. Min Act: -0.0000

Data Index: 1095482 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.9555. Min Act: -0.0001

Data Index: 628524 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.9853. Min Act: -0.0001

Data Index: 670618 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.0517. Min Act: -0.0001

Data Index: 974005 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.0126. Min Act: -0.0000

Data Index: 389428 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.0108. Min Act: -0.0001

Data Index: 1031000 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.0097. Min Act: -0.0001

Data Index: 504772 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.0284. Min Act: -0.0001

Data Index: 203368 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.0215. Min Act: -0.0001

Data Index: 214066 (C4 (Web Text))

Max Activating Token Index: 264