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

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

Neuron 3809 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: 0.0504. Min Range: -0.0504

Max Act: 0.0504. Min Act: -0.0002

Data Index: 163331 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1408008 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0437. Min Act: -0.0002

Data Index: 682328 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0398. Min Act: -0.0002

Data Index: 294932 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0378. Min Act: -0.0002

Data Index: 745574 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1576306 (Python Code)

Max Activating Token Index: 796

Text #6

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0373. Min Act: -0.0002

Data Index: 793689 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0367. Min Act: -0.0002

Data Index: 202891 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0380. Min Act: -0.0002

Data Index: 590747 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0378. Min Act: -0.0002

Data Index: 978991 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1331535 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0360. Min Act: -0.0002

Data Index: 525900 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1057525 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0337. Min Act: -0.0002

Data Index: 371757 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0332. Min Act: -0.0003

Data Index: 841606 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1258250 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0332. Min Act: -0.0002

Data Index: 15254 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1584905 (Python Code)

Max Activating Token Index: 1009

Text #18

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1607717 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1485865 (Python Code)

Max Activating Token Index: 1021