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

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

Neuron 64 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: 0.0410. Min Range: -0.0410

Max Act: 0.0406. Min Act: -0.0003

Data Index: 282802 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0003

Data Index: 245072 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0409. Min Act: -0.0004

Data Index: 1265819 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1332999 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1335502 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0387. Min Act: -0.0003

Data Index: 956992 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0380. Min Act: -0.0003

Data Index: 659591 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0388. Min Act: -0.0003

Data Index: 642255 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0380. Min Act: -0.0004

Data Index: 851553 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1062286 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1039069 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0381. Min Act: -0.0004

Data Index: 1200475 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0374. Min Act: -0.0004

Data Index: 714727 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1154949 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0375. Min Act: -0.0003

Data Index: 927050 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0367. Min Act: -0.0003

Data Index: 868637 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1273417 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0345. Min Act: -0.0003

Data Index: 121055 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0349. Min Act: -0.0003

Data Index: 40580 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0363. Min Act: -0.0002

Data Index: 119970 (C4 (Web Text))

Max Activating Token Index: 50