Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 187 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1113766 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0433. Min Act: -0.0002

Data Index: 342820 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1021787 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0423. Min Act: -0.0002

Data Index: 801268 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0416. Min Act: -0.0002

Data Index: 47445 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0411. Min Act: -0.0002

Data Index: 736341 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0407. Min Act: -0.0002

Data Index: 583657 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1047313 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0412. Min Act: -0.0002

Data Index: 643234 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1004064 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0403. Min Act: -0.0002

Data Index: 831947 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0418. Min Act: -0.0002

Data Index: 900217 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1129796 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0380. Min Act: -0.0002

Data Index: 778155 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1242137 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0378. Min Act: -0.0002

Data Index: 581772 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0383. Min Act: -0.0001

Data Index: 700943 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0377. Min Act: -0.0002

Data Index: 398551 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1121207 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0381. Min Act: -0.0002

Data Index: 878816 (C4 (Web Text))

Max Activating Token Index: 639