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

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

Neuron 1405 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2361. Min Act: -0.0001

Data Index: 231434 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2002. Min Act: -0.0001

Data Index: 1220662 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1039677 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1845. Min Act: -0.0001

Data Index: 647884 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1997. Min Act: -0.0001

Data Index: 453855 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1179743 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1735. Min Act: -0.0001

Data Index: 612950 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1139046 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1093640 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1614. Min Act: -0.0001

Data Index: 86465 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1763. Min Act: -0.0001

Data Index: 459548 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1622. Min Act: -0.0000

Data Index: 879862 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1566. Min Act: -0.0001

Data Index: 221827 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1103702 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1273983 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1627. Min Act: -0.0001

Data Index: 507101 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1628. Min Act: -0.0001

Data Index: 841346 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1647. Min Act: -0.0001

Data Index: 391685 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1538. Min Act: -0.0001

Data Index: 631239 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1559. Min Act: -0.0001

Data Index: 709439 (C4 (Web Text))

Max Activating Token Index: 300