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

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

Neuron 4331 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1552880 (Python Code)

Max Activating Token Index: 719

Text #1

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1539880 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0594. Min Act: -0.0000

Data Index: 652089 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1569405 (Python Code)

Max Activating Token Index: 505

Text #4

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0584. Min Act: -0.0000

Data Index: 895789 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0588. Min Act: -0.0000

Data Index: 889033 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1481734 (Python Code)

Max Activating Token Index: 246

Text #7

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1158830 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1548455 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0559. Min Act: -0.0000

Data Index: 21014 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1423431 (Python Code)

Max Activating Token Index: 358

Text #11

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0476. Min Act: -0.0000

Data Index: 1505373 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1584145 (Python Code)

Max Activating Token Index: 488

Text #13

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0491. Min Act: -0.0000

Data Index: 331862 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0455. Min Act: -0.0000

Data Index: 1619477 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0451. Min Act: -0.0000

Data Index: 958154 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0485. Min Act: -0.0000

Data Index: 341228 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1511285 (Python Code)

Max Activating Token Index: 297

Text #18

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1345459 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1056179 (C4 (Web Text))

Max Activating Token Index: 161