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

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

Neuron 3864 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2349. Min Act: -0.0000

Data Index: 770533 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2123. Min Act: -0.0000

Data Index: 764809 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1991. Min Act: -0.0000

Data Index: 498998 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1121383 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1178824 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1768. Min Act: -0.0000

Data Index: 929447 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1753. Min Act: -0.0000

Data Index: 416546 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1754. Min Act: -0.0000

Data Index: 650538 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1770. Min Act: -0.0000

Data Index: 519993 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1273573 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1615. Min Act: -0.0000

Data Index: 142500 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1149754 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1636. Min Act: -0.0000

Data Index: 792623 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1807. Min Act: -0.0000

Data Index: 629795 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1316150 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1707. Min Act: -0.0000

Data Index: 39875 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1568. Min Act: -0.0000

Data Index: 7216 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1567. Min Act: -0.0000

Data Index: 573442 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1604. Min Act: -0.0000

Data Index: 466146 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1525. Min Act: -0.0000

Data Index: 12085 (C4 (Web Text))

Max Activating Token Index: 19