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

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

Neuron 1449 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: 0.9518. Min Range: -0.9518

Max Act: 0.9518. Min Act: -0.0001

Data Index: 1094131 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.8451. Min Act: -0.0001

Data Index: 588929 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.9122. Min Act: -0.0001

Data Index: 1337398 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.8818. Min Act: -0.0001

Data Index: 822419 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.8722. Min Act: -0.0001

Data Index: 711078 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.8775. Min Act: -0.0001

Data Index: 1172178 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.8435. Min Act: -0.0001

Data Index: 577217 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.8125. Min Act: -0.0001

Data Index: 496532 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7685. Min Act: -0.0001

Data Index: 1636312 (Python Code)

Max Activating Token Index: 663

Text #9

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.8414. Min Act: -0.0001

Data Index: 818762 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7689. Min Act: -0.0001

Data Index: 734851 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7432. Min Act: -0.0001

Data Index: 607167 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7556. Min Act: -0.0001

Data Index: 1585974 (Python Code)

Max Activating Token Index: 944

Text #13

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7551. Min Act: -0.0001

Data Index: 1248967 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7364. Min Act: -0.0001

Data Index: 1506439 (Python Code)

Max Activating Token Index: 649

Text #15

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7605. Min Act: -0.0001

Data Index: 691888 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.6767. Min Act: -0.0001

Data Index: 475968 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7367. Min Act: -0.0001

Data Index: 242695 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7040. Min Act: -0.0001

Data Index: 499794 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7170. Min Act: -0.0001

Data Index: 1200187 (C4 (Web Text))

Max Activating Token Index: 899