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

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

Neuron 45 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.4473. Min Act: -0.0001

Data Index: 849542 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.4263. Min Act: -0.0001

Data Index: 914920 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.3018. Min Act: -0.0001

Data Index: 1270696 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.2467. Min Act: -0.0001

Data Index: 508921 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.2286. Min Act: -0.0001

Data Index: 1337870 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1602. Min Act: -0.0001

Data Index: 551460 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1887. Min Act: -0.0001

Data Index: 180045 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1848. Min Act: -0.0001

Data Index: 1225011 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1798. Min Act: -0.0001

Data Index: 1290877 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1612. Min Act: -0.0001

Data Index: 893194 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1238. Min Act: -0.0001

Data Index: 840714 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1141. Min Act: -0.0001

Data Index: 24315 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1058. Min Act: -0.0001

Data Index: 334391 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0685. Min Act: -0.0001

Data Index: 1148309 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0880. Min Act: -0.0001

Data Index: 205808 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0000. Min Act: -0.0001

Data Index: 568978 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0024. Min Act: -0.0001

Data Index: 462381 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9674. Min Act: -0.0001

Data Index: 1270632 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0511. Min Act: -0.0001

Data Index: 898941 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0169. Min Act: -0.0001

Data Index: 208406 (C4 (Web Text))

Max Activating Token Index: 1002