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

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

Neuron 4054 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: 0.0804. Min Range: -0.0804

Max Act: 0.0804. Min Act: -0.0000

Data Index: 521710 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0589. Min Act: -0.0000

Data Index: 941199 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0416. Min Act: -0.0000

Data Index: 114766 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0398. Min Act: -0.0000

Data Index: 1321415 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1034307 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0386. Min Act: -0.0000

Data Index: 814485 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1083916 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0344. Min Act: -0.0000

Data Index: 856026 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0364. Min Act: -0.0000

Data Index: 677841 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0336. Min Act: -0.0000

Data Index: 371465 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1030686 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0330. Min Act: -0.0000

Data Index: 749618 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0355. Min Act: -0.0000

Data Index: 17565 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0326. Min Act: -0.0000

Data Index: 422823 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1205002 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1530784 (Python Code)

Max Activating Token Index: 306

Text #16

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1262181 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0353. Min Act: -0.0000

Data Index: 1284622 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0315. Min Act: -0.0000

Data Index: 816275 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0315. Min Act: -0.0000

Data Index: 969624 (C4 (Web Text))

Max Activating Token Index: 104