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

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

Neuron 306 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: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0001

Data Index: 841576 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0411. Min Act: 0.0001

Data Index: 679379 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0412. Min Act: -0.0002

Data Index: 842670 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0401. Min Act: -0.0002

Data Index: 363041 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0403. Min Act: -0.0002

Data Index: 733579 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0394. Min Act: -0.0002

Data Index: 914327 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0379. Min Act: -0.0002

Data Index: 410887 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0380. Min Act: -0.0002

Data Index: 218016 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0369. Min Act: -0.0002

Data Index: 650437 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1267439 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0359. Min Act: -0.0002

Data Index: 488058 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1117064 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0350. Min Act: -0.0001

Data Index: 214551 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0359. Min Act: -0.0002

Data Index: 517269 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1071893 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0349. Min Act: -0.0001

Data Index: 173433 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0350. Min Act: -0.0001

Data Index: 266742 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0345. Min Act: -0.0002

Data Index: 509951 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0348. Min Act: -0.0002

Data Index: 857324 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1023158 (C4 (Web Text))

Max Activating Token Index: 214