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

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

Neuron 1040 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: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1581003 (Python Code)

Max Activating Token Index: 428

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1108884 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0400. Min Act: -0.0004

Data Index: 1619684 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0385. Min Act: -0.0003

Data Index: 120791 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1024627 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0380. Min Act: -0.0002

Data Index: 394097 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1298536 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1106870 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1092025 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1026602 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1150385 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0341. Min Act: -0.0003

Data Index: 807053 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0357. Min Act: -0.0003

Data Index: 771812 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1173651 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0361. Min Act: -0.0003

Data Index: 199006 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0347. Min Act: -0.0002

Data Index: 144392 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0342. Min Act: -0.0003

Data Index: 920473 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0347. Min Act: -0.0003

Data Index: 27827 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1047159 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1038291 (C4 (Web Text))

Max Activating Token Index: 596