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

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

Neuron 167 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: 0.2403. Min Range: -0.2403

Max Act: 0.2403. Min Act: -0.0000

Data Index: 471848 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1622. Min Act: -0.0000

Data Index: 370114 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1302. Min Act: -0.0000

Data Index: 386288 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1424859 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1254. Min Act: -0.0000

Data Index: 710541 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2248. Min Act: -0.0000

Data Index: 418577 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0909. Min Act: -0.0000

Data Index: 890752 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1593064 (Python Code)

Max Activating Token Index: 389

Text #8

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0886. Min Act: -0.0000

Data Index: 847453 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0835. Min Act: -0.0001

Data Index: 1411269 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1484541 (Python Code)

Max Activating Token Index: 1008

Text #11

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0830. Min Act: -0.0000

Data Index: 875163 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0799. Min Act: -0.0000

Data Index: 765226 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0813. Min Act: -0.0001

Data Index: 970471 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1319. Min Act: -0.0000

Data Index: 601626 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1423224 (Python Code)

Max Activating Token Index: 610

Text #16

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1403641 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1415865 (Python Code)

Max Activating Token Index: 590

Text #18

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1397637 (Python Code)

Max Activating Token Index: 684

Text #19

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.0773. Min Act: -0.0001

Data Index: 284752 (C4 (Web Text))

Max Activating Token Index: 334