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

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

Neuron 4230 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: 0.1904. Min Range: -0.1904

Max Act: 0.1904. Min Act: -0.0003

Data Index: 174110 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1713. Min Act: -0.0003

Data Index: 157498 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1610. Min Act: -0.0003

Data Index: 73114 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1247. Min Act: -0.0003

Data Index: 1328893 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1130. Min Act: -0.0003

Data Index: 752408 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1183. Min Act: -0.0003

Data Index: 452490 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1250. Min Act: -0.0003

Data Index: 817001 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1118. Min Act: -0.0003

Data Index: 174420 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1162. Min Act: -0.0003

Data Index: 695309 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1101. Min Act: -0.0003

Data Index: 1247402 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.0899. Min Act: -0.0003

Data Index: 209692 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1076. Min Act: -0.0003

Data Index: 93805 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.0952. Min Act: -0.0003

Data Index: 49722 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1071. Min Act: -0.0003

Data Index: 252335 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.0966. Min Act: -0.0003

Data Index: 1289780 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1107. Min Act: -0.0003

Data Index: 778207 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.0748. Min Act: -0.0002

Data Index: 918744 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1162. Min Act: -0.0003

Data Index: 88055 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1180. Min Act: -0.0003

Data Index: 351715 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.0954. Min Act: -0.0002

Data Index: 210785 (C4 (Web Text))

Max Activating Token Index: 726