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

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

Neuron 2753 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1317526 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0444. Min Act: -0.0003

Data Index: 224798 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0460. Min Act: -0.0002

Data Index: 283075 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0444. Min Act: -0.0002

Data Index: 206401 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1092913 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1158890 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0440. Min Act: -0.0003

Data Index: 159198 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1014865 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0412. Min Act: -0.0002

Data Index: 251944 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0411. Min Act: -0.0002

Data Index: 353491 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0407. Min Act: -0.0003

Data Index: 317897 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1084049 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0394. Min Act: -0.0002

Data Index: 208534 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0370. Min Act: -0.0002

Data Index: 748852 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1231781 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0384. Min Act: -0.0002

Data Index: 422613 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0379. Min Act: -0.0002

Data Index: 659075 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0378. Min Act: -0.0002

Data Index: 42846 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0382. Min Act: -0.0003

Data Index: 497705 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0380. Min Act: -0.0002

Data Index: 670280 (C4 (Web Text))

Max Activating Token Index: 65