Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 401 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2468. Min Act: -0.0002

Data Index: 1181804 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2119. Min Act: -0.0002

Data Index: 1027703 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2240. Min Act: -0.0002

Data Index: 286030 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2153. Min Act: -0.0002

Data Index: 1080430 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2132. Min Act: -0.0002

Data Index: 748029 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2206. Min Act: -0.0001

Data Index: 568900 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1948. Min Act: -0.0001

Data Index: 732464 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2032. Min Act: -0.0002

Data Index: 723105 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2010. Min Act: -0.0001

Data Index: 175389 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1883. Min Act: -0.0001

Data Index: 969680 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1933. Min Act: -0.0001

Data Index: 760414 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1951. Min Act: -0.0002

Data Index: 941525 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1869. Min Act: -0.0002

Data Index: 719123 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1800. Min Act: -0.0002

Data Index: 451520 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1851. Min Act: -0.0002

Data Index: 100544 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1846. Min Act: -0.0002

Data Index: 42376 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1954. Min Act: -0.0001

Data Index: 660101 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1748. Min Act: -0.0002

Data Index: 1311123 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1781. Min Act: -0.0002

Data Index: 167421 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1797. Min Act: -0.0002

Data Index: 178525 (C4 (Web Text))

Max Activating Token Index: 671