Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5267 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.3023. Min Act: -0.0000

Data Index: 732392 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1621886 (Python Code)

Max Activating Token Index: 883

Text #2

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1542101 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2571. Min Act: -0.0000

Data Index: 700513 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1120085 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1456004 (Python Code)

Max Activating Token Index: 937

Text #6

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2573. Min Act: -0.0000

Data Index: 563662 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1541521 (Python Code)

Max Activating Token Index: 706

Text #8

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2334. Min Act: -0.0000

Data Index: 473109 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1387949 (Python Code)

Max Activating Token Index: 1004

Text #10

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1413009 (Python Code)

Max Activating Token Index: 908

Text #11

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1382586 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1374944 (Python Code)

Max Activating Token Index: 952

Text #13

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1419780 (Python Code)

Max Activating Token Index: 878

Text #14

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1534256 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1218610 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2033. Min Act: -0.0000

Data Index: 472834 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2174. Min Act: -0.0000

Data Index: 213188 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1365562 (Python Code)

Max Activating Token Index: 994

Text #19

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1444377 (Python Code)

Max Activating Token Index: 1006