Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4364 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1293870 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1617454 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1243618 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1419584 (Python Code)

Max Activating Token Index: 111

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1231042 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0564. Min Act: -0.0000

Data Index: 146798 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1079538 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0543. Min Act: -0.0000

Data Index: 84523 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1258931 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0473. Min Act: -0.0000

Data Index: 658586 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0473. Min Act: -0.0000

Data Index: 986560 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1113729 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0499. Min Act: -0.0000

Data Index: 199142 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0444. Min Act: -0.0000

Data Index: 1218658 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0447. Min Act: -0.0000

Data Index: 843720 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0425. Min Act: -0.0000

Data Index: 100670 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0440. Min Act: -0.0000

Data Index: 22248 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1269912 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0401. Min Act: -0.0000

Data Index: 56315 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0413. Min Act: -0.0000

Data Index: 1056369 (C4 (Web Text))

Max Activating Token Index: 625