Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 909 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1672. Min Act: -0.0001

Data Index: 673348 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1716. Min Act: -0.0001

Data Index: 470208 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1693. Min Act: -0.0001

Data Index: 173355 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1740. Min Act: -0.0001

Data Index: 19304 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1727. Min Act: -0.0001

Data Index: 748039 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1545. Min Act: -0.0001

Data Index: 914774 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1701. Min Act: -0.0001

Data Index: 931414 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1282256 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1577. Min Act: -0.0001

Data Index: 431328 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1594. Min Act: -0.0001

Data Index: 261991 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1585. Min Act: -0.0001

Data Index: 659188 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1520. Min Act: -0.0001

Data Index: 1119746 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1513. Min Act: -0.0001

Data Index: 435880 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1563. Min Act: -0.0001

Data Index: 726443 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1420. Min Act: -0.0001

Data Index: 149169 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1071138 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1447. Min Act: -0.0001

Data Index: 936256 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1500. Min Act: -0.0001

Data Index: 643799 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1490. Min Act: -0.0001

Data Index: 182772 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1443. Min Act: -0.0001

Data Index: 223947 (C4 (Web Text))

Max Activating Token Index: 525