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

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

Neuron 1991 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: 0.0456. Min Range: -0.0456

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1157121 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0442. Min Act: -0.0003

Data Index: 51293 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0003

Data Index: 9596 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0432. Min Act: -0.0003

Data Index: 60224 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1279164 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1280979 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1048906 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1055759 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0439. Min Act: -0.0003

Data Index: 586723 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0409. Min Act: -0.0003

Data Index: 438687 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0423. Min Act: -0.0003

Data Index: 131460 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1219366 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0421. Min Act: -0.0004

Data Index: 137364 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0418. Min Act: -0.0003

Data Index: 924926 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0438. Min Act: -0.0003

Data Index: 793665 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1333253 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0406. Min Act: -0.0004

Data Index: 477883 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0408. Min Act: -0.0003

Data Index: 256115 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0395. Min Act: -0.0003

Data Index: 919617 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0394. Min Act: -0.0004

Data Index: 967664 (C4 (Web Text))

Max Activating Token Index: 690