Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4485 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1087551 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0553. Min Act: -0.0000

Data Index: 370143 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0607. Min Act: -0.0000

Data Index: 140406 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0476. Min Act: -0.0001

Data Index: 531186 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1112013 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0372. Min Act: -0.0000

Data Index: 18235 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0403. Min Act: -0.0001

Data Index: 942706 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0419. Min Act: -0.0000

Data Index: 1175779 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0455. Min Act: -0.0000

Data Index: 672209 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1186404 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0405. Min Act: -0.0000

Data Index: 319194 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0547. Min Act: -0.0000

Data Index: 911609 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0393. Min Act: -0.0000

Data Index: 435590 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1175244 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0415. Min Act: -0.0000

Data Index: 433586 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0394. Min Act: -0.0000

Data Index: 387326 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0360. Min Act: -0.0000

Data Index: 106947 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0392. Min Act: -0.0000

Data Index: 746455 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1164826 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0362. Min Act: -0.0000

Data Index: 807666 (C4 (Web Text))

Max Activating Token Index: 196