Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 321 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.2053. Min Act: -0.0003

Data Index: 388358 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1935. Min Act: -0.0004

Data Index: 852240 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1906. Min Act: -0.0003

Data Index: 774784 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1809. Min Act: -0.0003

Data Index: 939632 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1790. Min Act: -0.0001

Data Index: 857178 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1736. Min Act: -0.0003

Data Index: 785582 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1700. Min Act: -0.0003

Data Index: 360898 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1724. Min Act: -0.0003

Data Index: 1150874 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1660. Min Act: -0.0003

Data Index: 643589 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1671. Min Act: -0.0003

Data Index: 567212 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1673. Min Act: -0.0003

Data Index: 1180086 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1667. Min Act: -0.0002

Data Index: 944290 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1655. Min Act: -0.0002

Data Index: 1354293 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1648. Min Act: -0.0002

Data Index: 543630 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1673. Min Act: -0.0003

Data Index: 63242 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1609. Min Act: -0.0003

Data Index: 638526 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1642. Min Act: -0.0003

Data Index: 1157303 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1619. Min Act: -0.0003

Data Index: 554849 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1587. Min Act: -0.0003

Data Index: 175473 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.2053. Min Range: -0.2053

Max Act: 0.1595. Min Act: -0.0003

Data Index: 180694 (C4 (Web Text))

Max Activating Token Index: 889