Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0429. Min Act: -0.0004

Data Index: 5803 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0410. Min Act: -0.0003

Data Index: 347477 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0411. Min Act: -0.0002

Data Index: 268380 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0418. Min Act: -0.0003

Data Index: 216555 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0403. Min Act: -0.0003

Data Index: 192446 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0383. Min Act: -0.0003

Data Index: 588765 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0391. Min Act: 0.0000

Data Index: 133477 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0374. Min Act: 0.0001

Data Index: 753648 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0370. Min Act: -0.0002

Data Index: 214742 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1021535 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0374. Min Act: -0.0001

Data Index: 169406 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0366. Min Act: -0.0003

Data Index: 429042 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1228359 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0354. Min Act: 0.0000

Data Index: 649022 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0357. Min Act: 0.0001

Data Index: 123481 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0360. Min Act: -0.0004

Data Index: 860252 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1114024 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0342. Min Act: -0.0003

Data Index: 990094 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1275349 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1078421 (C4 (Web Text))

Max Activating Token Index: 14