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

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

Neuron 3768 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.4187. Min Act: -0.0001

Data Index: 1191554 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7970. Min Act: -0.0001

Data Index: 458656 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7301. Min Act: -0.0001

Data Index: 943521 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7954. Min Act: -0.0001

Data Index: 296553 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7119. Min Act: -0.0001

Data Index: 970114 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.6540. Min Act: -0.0001

Data Index: 1218533 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7719. Min Act: -0.0002

Data Index: 1007822 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7673. Min Act: -0.0001

Data Index: 369250 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.5958. Min Act: -0.0001

Data Index: 871619 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.5226. Min Act: -0.0001

Data Index: 1034294 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.6886. Min Act: -0.0002

Data Index: 600418 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.6166. Min Act: -0.0001

Data Index: 967281 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.5991. Min Act: -0.0001

Data Index: 1249760 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.4657. Min Act: -0.0001

Data Index: 1252655 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.6347. Min Act: -0.0001

Data Index: 473093 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.6754. Min Act: -0.0001

Data Index: 153982 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.3951. Min Act: -0.0002

Data Index: 928728 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.6076. Min Act: -0.0001

Data Index: 952882 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.5682. Min Act: -0.0001

Data Index: 217569 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.4329. Min Act: -0.0001

Data Index: 762697 (C4 (Web Text))

Max Activating Token Index: 61