Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1394 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2423. Min Act: -0.0003

Data Index: 1582446 (Python Code)

Max Activating Token Index: 900

Text #1

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2330. Min Act: -0.0003

Data Index: 409532 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2044. Min Act: -0.0003

Data Index: 489603 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2255. Min Act: -0.0003

Data Index: 419982 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2389. Min Act: -0.0003

Data Index: 1586830 (Python Code)

Max Activating Token Index: 722

Text #5

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1999. Min Act: -0.0003

Data Index: 826128 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2052. Min Act: -0.0003

Data Index: 707717 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2200. Min Act: -0.0003

Data Index: 697143 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2171. Min Act: -0.0003

Data Index: 1330275 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2183. Min Act: -0.0003

Data Index: 169629 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2298. Min Act: -0.0003

Data Index: 779836 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2120. Min Act: -0.0003

Data Index: 976768 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1908. Min Act: -0.0003

Data Index: 920535 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2064. Min Act: -0.0003

Data Index: 595079 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2002. Min Act: -0.0003

Data Index: 1515356 (Python Code)

Max Activating Token Index: 742

Text #15

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2229. Min Act: -0.0003

Data Index: 775207 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2142. Min Act: -0.0003

Data Index: 1447244 (Python Code)

Max Activating Token Index: 860

Text #17

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2187. Min Act: -0.0003

Data Index: 798780 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2123. Min Act: -0.0003

Data Index: 360495 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1820. Min Act: -0.0003

Data Index: 442613 (C4 (Web Text))

Max Activating Token Index: 639