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

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

Neuron 4984 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1517670 (Python Code)

Max Activating Token Index: 666

Text #1

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1580227 (Python Code)

Max Activating Token Index: 534

Text #2

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1407339 (Python Code)

Max Activating Token Index: 216

Text #3

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1472084 (Python Code)

Max Activating Token Index: 587

Text #4

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1632098 (Python Code)

Max Activating Token Index: 814

Text #5

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1591666 (Python Code)

Max Activating Token Index: 905

Text #6

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1456277 (Python Code)

Max Activating Token Index: 913

Text #7

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1648615 (Python Code)

Max Activating Token Index: 945

Text #8

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1552044 (Python Code)

Max Activating Token Index: 847

Text #9

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1444100 (Python Code)

Max Activating Token Index: 558

Text #10

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1591124 (Python Code)

Max Activating Token Index: 916

Text #11

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1653721 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1532379 (Python Code)

Max Activating Token Index: 649

Text #13

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1399829 (Python Code)

Max Activating Token Index: 133

Text #14

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1462590 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1563476 (Python Code)

Max Activating Token Index: 359

Text #16

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1608451 (Python Code)

Max Activating Token Index: 199

Text #17

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1599088 (Python Code)

Max Activating Token Index: 397

Text #18

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1415391 (Python Code)

Max Activating Token Index: 818

Text #19

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1572391 (Python Code)

Max Activating Token Index: 877