Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1243 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1436806 (Python Code)

Max Activating Token Index: 648

Text #1

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1540982 (Python Code)

Max Activating Token Index: 747

Text #2

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0401. Min Act: -0.0001

Data Index: 382062 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0391. Min Act: -0.0001

Data Index: 610140 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1522591 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0385. Min Act: -0.0001

Data Index: 680916 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0373. Min Act: -0.0001

Data Index: 967532 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1497882 (Python Code)

Max Activating Token Index: 215

Text #8

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1341033 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0348. Min Act: -0.0001

Data Index: 811692 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1467273 (Python Code)

Max Activating Token Index: 878

Text #11

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1427376 (Python Code)

Max Activating Token Index: 764

Text #12

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1430041 (Python Code)

Max Activating Token Index: 450

Text #13

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1467415 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1582475 (Python Code)

Max Activating Token Index: 554

Text #15

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1309727 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1625618 (Python Code)

Max Activating Token Index: 408

Text #17

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1386377 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1441508 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0320. Min Act: -0.0001

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 215