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

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

Neuron 2462 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0543. Min Act: -0.0002

Data Index: 623943 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0458. Min Act: -0.0002

Data Index: 261799 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0445. Min Act: -0.0002

Data Index: 482225 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0434. Min Act: -0.0002

Data Index: 294385 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1423196 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0405. Min Act: -0.0002

Data Index: 444730 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0371. Min Act: -0.0002

Data Index: 75344 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1352792 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1061958 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0360. Min Act: -0.0002

Data Index: 422311 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0373. Min Act: -0.0002

Data Index: 152050 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0360. Min Act: -0.0002

Data Index: 500670 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1635460 (Python Code)

Max Activating Token Index: 992

Text #13

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0336. Min Act: -0.0002

Data Index: 581780 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0337. Min Act: -0.0002

Data Index: 940331 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1399724 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0340. Min Act: -0.0002

Data Index: 791585 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0339. Min Act: -0.0002

Data Index: 896548 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0319. Min Act: -0.0002

Data Index: 793937 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1138070 (C4 (Web Text))

Max Activating Token Index: 879