Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 652 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0886. Min Act: -0.0005

Data Index: 1468395 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0852. Min Act: -0.0005

Data Index: 1436954 (Python Code)

Max Activating Token Index: 983

Text #2

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0689. Min Act: -0.0005

Data Index: 1055714 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0486. Min Act: -0.0006

Data Index: 453458 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0479. Min Act: -0.0005

Data Index: 1501421 (Python Code)

Max Activating Token Index: 945

Text #5

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0458. Min Act: -0.0005

Data Index: 1506790 (Python Code)

Max Activating Token Index: 960

Text #6

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0428. Min Act: -0.0005

Data Index: 1502343 (Python Code)

Max Activating Token Index: 1018

Text #7

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0417. Min Act: -0.0005

Data Index: 1509406 (Python Code)

Max Activating Token Index: 884

Text #8

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0418. Min Act: -0.0005

Data Index: 1481843 (Python Code)

Max Activating Token Index: 904

Text #9

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0418. Min Act: -0.0005

Data Index: 1427172 (Python Code)

Max Activating Token Index: 897

Text #10

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0400. Min Act: -0.0005

Data Index: 1475556 (Python Code)

Max Activating Token Index: 898

Text #11

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0388. Min Act: -0.0006

Data Index: 767312 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0383. Min Act: -0.0005

Data Index: 1404319 (Python Code)

Max Activating Token Index: 899

Text #13

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0378. Min Act: -0.0005

Data Index: 617150 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0364. Min Act: -0.0005

Data Index: 491695 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0369. Min Act: -0.0005

Data Index: 1638658 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0365. Min Act: -0.0005

Data Index: 1450599 (Python Code)

Max Activating Token Index: 982

Text #17

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0355. Min Act: -0.0005

Data Index: 1502512 (Python Code)

Max Activating Token Index: 810

Text #18

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0355. Min Act: -0.0005

Data Index: 1462513 (Python Code)

Max Activating Token Index: 937

Text #19

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0361. Min Act: -0.0005

Data Index: 1500666 (Python Code)

Max Activating Token Index: 903