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

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

Neuron 959 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: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0000

Data Index: 356365 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0493. Min Act: -0.0000

Data Index: 96080 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0484. Min Act: -0.0000

Data Index: 807866 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0467. Min Act: -0.0000

Data Index: 1177545 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0465. Min Act: -0.0000

Data Index: 225353 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0461. Min Act: -0.0000

Data Index: 915357 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0472. Min Act: -0.0000

Data Index: 982664 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0447. Min Act: -0.0000

Data Index: 234995 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1441946 (Python Code)

Max Activating Token Index: 843

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0428. Min Act: -0.0000

Data Index: 1088932 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0423. Min Act: -0.0000

Data Index: 1009714 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0414. Min Act: -0.0000

Data Index: 363889 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0409. Min Act: -0.0000

Data Index: 541917 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0390. Min Act: -0.0000

Data Index: 476792 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1582999 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0386. Min Act: -0.0000

Data Index: 200287 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0391. Min Act: -0.0000

Data Index: 969324 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1314873 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1163663 (C4 (Web Text))

Max Activating Token Index: 702