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

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

Neuron 1892 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: 0.0097. Min Range: -0.0097

Max Act: 0.0097. Min Act: -0.0003

Data Index: 110430 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0091. Min Act: -0.0003

Data Index: 147372 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0088. Min Act: -0.0003

Data Index: 611834 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0087. Min Act: -0.0003

Data Index: 69210 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0086. Min Act: -0.0003

Data Index: 782709 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1605065 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1094633 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1066785 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0082. Min Act: -0.0003

Data Index: 361254 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0081. Min Act: -0.0003

Data Index: 518512 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0083. Min Act: -0.0003

Data Index: 74669 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0081. Min Act: -0.0003

Data Index: 95016 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0080. Min Act: -0.0003

Data Index: 627399 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0080. Min Act: -0.0003

Data Index: 507050 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0079. Min Act: -0.0003

Data Index: 697334 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0079. Min Act: -0.0003

Data Index: 567799 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0080. Min Act: -0.0003

Data Index: 510658 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0078. Min Act: -0.0003

Data Index: 309208 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0078. Min Act: -0.0003

Data Index: 964357 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0078. Min Act: -0.0003

Data Index: 902764 (C4 (Web Text))

Max Activating Token Index: 13