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

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

Neuron 5424 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1508038 (Python Code)

Max Activating Token Index: 992

Text #1

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1461764 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0422. Min Act: -0.0002

Data Index: 581769 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1407313 (Python Code)

Max Activating Token Index: 844

Text #4

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1603767 (Python Code)

Max Activating Token Index: 1005

Text #5

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1519305 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1483890 (Python Code)

Max Activating Token Index: 1010

Text #7

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1221988 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0388. Min Act: -0.0002

Data Index: 88897 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1567764 (Python Code)

Max Activating Token Index: 1002

Text #10

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0381. Min Act: -0.0002

Data Index: 551268 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1479122 (Python Code)

Max Activating Token Index: 1019

Text #12

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0372. Min Act: -0.0002

Data Index: 967999 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1603006 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1391099 (Python Code)

Max Activating Token Index: 1014

Text #15

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1574890 (Python Code)

Max Activating Token Index: 987

Text #16

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1382418 (Python Code)

Max Activating Token Index: 1005

Text #17

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1486903 (Python Code)

Max Activating Token Index: 988

Text #18

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1146388 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0334. Min Act: -0.0002

Data Index: 916455 (C4 (Web Text))

Max Activating Token Index: 1007