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

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

Neuron 2213 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: 0.6811. Min Range: -0.6811

Max Act: 0.6811. Min Act: -0.0001

Data Index: 679492 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.6769. Min Act: -0.0001

Data Index: 791758 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.6314. Min Act: -0.0001

Data Index: 1254731 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.6172. Min Act: -0.0000

Data Index: 119272 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.6278. Min Act: -0.0001

Data Index: 796441 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.6159. Min Act: -0.0000

Data Index: 657806 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5944. Min Act: -0.0001

Data Index: 429425 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5821. Min Act: -0.0001

Data Index: 747068 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5843. Min Act: -0.0001

Data Index: 1345509 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5811. Min Act: -0.0001

Data Index: 990135 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5660. Min Act: -0.0001

Data Index: 872776 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5808. Min Act: -0.0001

Data Index: 878669 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5724. Min Act: -0.0001

Data Index: 16207 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5517. Min Act: -0.0001

Data Index: 1021607 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5669. Min Act: -0.0001

Data Index: 168350 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5658. Min Act: -0.0001

Data Index: 79514 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5604. Min Act: -0.0001

Data Index: 727077 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5755. Min Act: -0.0001

Data Index: 152174 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5774. Min Act: -0.0000

Data Index: 475648 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1325317 (C4 (Web Text))

Max Activating Token Index: 631