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

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

Neuron 1304 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1258695 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0006

Data Index: 1400107 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0391. Min Act: -0.0006

Data Index: 882380 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0403. Min Act: -0.0006

Data Index: 1255231 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1201372 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0390. Min Act: -0.0006

Data Index: 423870 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0398. Min Act: -0.0006

Data Index: 574941 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0384. Min Act: -0.0006

Data Index: 1639719 (Python Code)

Max Activating Token Index: 710

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0376. Min Act: -0.0006

Data Index: 701509 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0389. Min Act: -0.0006

Data Index: 143698 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0397. Min Act: -0.0006

Data Index: 113762 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0379. Min Act: -0.0006

Data Index: 1196856 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0384. Min Act: -0.0006

Data Index: 244604 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0367. Min Act: -0.0006

Data Index: 1623799 (Python Code)

Max Activating Token Index: 841

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0370. Min Act: -0.0006

Data Index: 1551643 (Python Code)

Max Activating Token Index: 939

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0364. Min Act: -0.0006

Data Index: 795898 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0362. Min Act: -0.0006

Data Index: 1628006 (Python Code)

Max Activating Token Index: 857

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0363. Min Act: -0.0006

Data Index: 879251 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1206354 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0374. Min Act: -0.0006

Data Index: 1378139 (Python Code)

Max Activating Token Index: 715