Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1074 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1761. Min Act: -0.0001

Data Index: 1226101 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1962. Min Act: -0.0001

Data Index: 156872 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1841. Min Act: -0.0001

Data Index: 432533 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1898. Min Act: -0.0001

Data Index: 1284057 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1763. Min Act: -0.0001

Data Index: 521478 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1648. Min Act: -0.0001

Data Index: 973432 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1258680 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1306385 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1741. Min Act: -0.0001

Data Index: 263416 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1667. Min Act: -0.0001

Data Index: 352708 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1711. Min Act: -0.0001

Data Index: 43254 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1576. Min Act: -0.0001

Data Index: 108636 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1691. Min Act: -0.0001

Data Index: 654812 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1685. Min Act: -0.0001

Data Index: 316996 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1615. Min Act: -0.0001

Data Index: 849158 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1752. Min Act: -0.0001

Data Index: 150058 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1009569 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1573. Min Act: -0.0001

Data Index: 65846 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1744. Min Act: -0.0001

Data Index: 434192 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1660. Min Act: -0.0001

Data Index: 997104 (C4 (Web Text))

Max Activating Token Index: 121