Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 725 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0451. Min Act: -0.0001

Data Index: 31267 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0441. Min Act: -0.0001

Data Index: 444316 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0435. Min Act: -0.0001

Data Index: 343860 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0427. Min Act: -0.0001

Data Index: 775535 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1121543 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0429. Min Act: -0.0001

Data Index: 201618 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1111434 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0415. Min Act: -0.0001

Data Index: 925140 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0428. Min Act: -0.0001

Data Index: 847149 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1300879 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0410. Min Act: -0.0001

Data Index: 705541 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1170570 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0420. Min Act: -0.0001

Data Index: 910603 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0425. Min Act: -0.0001

Data Index: 377748 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0409. Min Act: -0.0001

Data Index: 391043 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1302969 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0414. Min Act: -0.0001

Data Index: 865179 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0418. Min Act: -0.0001

Data Index: 465280 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0412. Min Act: -0.0001

Data Index: 862344 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0417. Min Act: -0.0001

Data Index: 69558 (C4 (Web Text))

Max Activating Token Index: 731