Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 332 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1601433 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1589530 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1609712 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1465649 (Python Code)

Max Activating Token Index: 403

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1591316 (Python Code)

Max Activating Token Index: 281

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1553686 (Python Code)

Max Activating Token Index: 506

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1394815 (Python Code)

Max Activating Token Index: 19

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1406121 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1622918 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1399746 (Python Code)

Max Activating Token Index: 301

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1527539 (Python Code)

Max Activating Token Index: 426

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1615537 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1590160 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1650111 (Python Code)

Max Activating Token Index: 537

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1423316 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1556342 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1474405 (Python Code)

Max Activating Token Index: 501

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1525016 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1597988 (Python Code)

Max Activating Token Index: 613

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1466298 (Python Code)

Max Activating Token Index: 417