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

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

Neuron 1974 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.3112. Min Act: -0.0001

Data Index: 1197470 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2538. Min Act: -0.0001

Data Index: 11290 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2329. Min Act: -0.0001

Data Index: 984812 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2334. Min Act: -0.0001

Data Index: 1101559 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2250. Min Act: -0.0001

Data Index: 1344351 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2115. Min Act: -0.0001

Data Index: 521596 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2064. Min Act: -0.0001

Data Index: 312012 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2043. Min Act: -0.0001

Data Index: 1321459 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1244320 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1352712 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2057. Min Act: -0.0000

Data Index: 485386 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2074. Min Act: -0.0001

Data Index: 975296 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2083. Min Act: -0.0001

Data Index: 715826 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2083. Min Act: -0.0001

Data Index: 887827 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2006. Min Act: -0.0001

Data Index: 271060 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1938. Min Act: -0.0001

Data Index: 892167 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1984. Min Act: -0.0001

Data Index: 884167 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1961. Min Act: -0.0001

Data Index: 488640 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1308396 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.1940. Min Act: -0.0001

Data Index: 629715 (C4 (Web Text))

Max Activating Token Index: 22