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

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

Neuron 1053 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: 0.2839. Min Range: -0.2839

Max Act: 0.2839. Min Act: -0.0001

Data Index: 482273 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1797. Min Act: -0.0001

Data Index: 368575 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1840. Min Act: -0.0001

Data Index: 983656 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1792. Min Act: -0.0001

Data Index: 570116 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1629. Min Act: -0.0001

Data Index: 757659 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1646. Min Act: -0.0001

Data Index: 95744 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1830. Min Act: -0.0001

Data Index: 468586 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1086091 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1529. Min Act: -0.0001

Data Index: 954943 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1358318 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1686. Min Act: -0.0001

Data Index: 810173 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1247587 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1659. Min Act: -0.0001

Data Index: 609520 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1541. Min Act: -0.0001

Data Index: 672696 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1705. Min Act: -0.0001

Data Index: 448540 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1621. Min Act: -0.0001

Data Index: 617787 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1338567 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1555. Min Act: -0.0001

Data Index: 811263 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1541. Min Act: -0.0001

Data Index: 765716 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.1546. Min Act: -0.0001

Data Index: 1055515 (C4 (Web Text))

Max Activating Token Index: 659