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

Dataset: The Pile

Neuron 311 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1276827 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1951066 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2038. Min Act: -0.0000

Data Index: 534512 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1581484 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1666. Min Act: -0.0000

Data Index: 689729 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1682. Min Act: -0.0000

Data Index: 380755 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1995801 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1461753 (The Pile)

Max Activating Token Index: 839

Text #8

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1604. Min Act: -0.0000

Data Index: 916442 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1647. Min Act: -0.0000

Data Index: 811772 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1231435 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1552. Min Act: -0.0000

Data Index: 502405 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1455415 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1485. Min Act: -0.0000

Data Index: 997323 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1437. Min Act: -0.0000

Data Index: 295547 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1304577 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1586. Min Act: -0.0000

Data Index: 208362 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1529354 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1195481 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1373039 (The Pile)

Max Activating Token Index: 684