Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1300 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0600. Min Act: -0.0003

Data Index: 38436 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0488. Min Act: -0.0003

Data Index: 844280 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1290761 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0477. Min Act: -0.0003

Data Index: 741530 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0453. Min Act: -0.0003

Data Index: 17350 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0468. Min Act: -0.0003

Data Index: 934759 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1303228 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0433. Min Act: -0.0003

Data Index: 414597 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0442. Min Act: -0.0003

Data Index: 80525 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0429. Min Act: -0.0003

Data Index: 671116 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0431. Min Act: -0.0003

Data Index: 794145 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0432. Min Act: -0.0003

Data Index: 59772 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0414. Min Act: -0.0003

Data Index: 514240 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0393. Min Act: -0.0003

Data Index: 957445 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0420. Min Act: -0.0003

Data Index: 244914 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0416. Min Act: -0.0003

Data Index: 103324 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0408. Min Act: -0.0003

Data Index: 462184 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0415. Min Act: -0.0003

Data Index: 7881 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1207284 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1136287 (C4 (Web Text))

Max Activating Token Index: 979