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

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

Neuron 2640 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1661. Min Act: -0.0002

Data Index: 1029540 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1653996 (Python Code)

Max Activating Token Index: 941

Text #2

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1559. Min Act: -0.0002

Data Index: 1149584 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1592. Min Act: -0.0001

Data Index: 219670 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1526. Min Act: -0.0002

Data Index: 726200 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1512. Min Act: -0.0001

Data Index: 553368 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1423. Min Act: -0.0002

Data Index: 912833 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1455. Min Act: -0.0001

Data Index: 630161 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1452. Min Act: -0.0002

Data Index: 303586 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1442. Min Act: -0.0001

Data Index: 276969 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1358. Min Act: -0.0002

Data Index: 989225 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1392. Min Act: -0.0002

Data Index: 443256 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1395. Min Act: -0.0002

Data Index: 416522 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1399. Min Act: -0.0001

Data Index: 973330 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1434. Min Act: -0.0002

Data Index: 719053 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1341. Min Act: -0.0001

Data Index: 642974 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1431. Min Act: -0.0001

Data Index: 576126 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1333. Min Act: -0.0001

Data Index: 546170 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1365. Min Act: -0.0002

Data Index: 1184567 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1407. Min Act: -0.0002

Data Index: 1055540 (C4 (Web Text))

Max Activating Token Index: 439