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

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

Neuron 2807 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1125108 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1593066 (Python Code)

Max Activating Token Index: 917

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1383443 (Python Code)

Max Activating Token Index: 864

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1301372 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1654311 (Python Code)

Max Activating Token Index: 824

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1628969 (Python Code)

Max Activating Token Index: 840

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1581047 (Python Code)

Max Activating Token Index: 931

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1515900 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1591522 (Python Code)

Max Activating Token Index: 1011

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1600848 (Python Code)

Max Activating Token Index: 918

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1529240 (Python Code)

Max Activating Token Index: 933

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0192. Min Act: -0.0002

Data Index: 429193 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1547799 (Python Code)

Max Activating Token Index: 982

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1476083 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1461713 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1502488 (Python Code)

Max Activating Token Index: 836

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1510618 (Python Code)

Max Activating Token Index: 990

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1063939 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0184. Min Act: -0.0001

Data Index: 1613475 (Python Code)

Max Activating Token Index: 989

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0193. Min Act: -0.0002

Data Index: 771542 (C4 (Web Text))

Max Activating Token Index: 785