Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1467 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1508039 (Python Code)

Max Activating Token Index: 240

Text #1

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0468. Min Act: -0.0000

Data Index: 810131 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1479529 (Python Code)

Max Activating Token Index: 887

Text #3

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1369924 (Python Code)

Max Activating Token Index: 648

Text #4

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1025823 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1639901 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1638279 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1573580 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1456866 (Python Code)

Max Activating Token Index: 198

Text #9

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1527136 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1621454 (Python Code)

Max Activating Token Index: 746

Text #11

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1610097 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0308. Min Act: -0.0000

Data Index: 842779 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0317. Min Act: -0.0000

Data Index: 542053 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0330. Min Act: -0.0000

Data Index: 1503068 (Python Code)

Max Activating Token Index: 1018

Text #15

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1539272 (Python Code)

Max Activating Token Index: 425

Text #16

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0292. Min Act: -0.0000

Data Index: 1500478 (Python Code)

Max Activating Token Index: 196

Text #17

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1533208 (Python Code)

Max Activating Token Index: 707

Text #18

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0315. Min Act: -0.0000

Data Index: 1436139 (Python Code)

Max Activating Token Index: 697

Text #19

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1445867 (Python Code)

Max Activating Token Index: 538