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

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

Neuron 1155 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1444. Min Act: -0.0001

Data Index: 823769 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1379. Min Act: -0.0001

Data Index: 225960 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1140. Min Act: -0.0001

Data Index: 354274 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1159. Min Act: -0.0001

Data Index: 695305 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1106. Min Act: -0.0001

Data Index: 751826 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1053. Min Act: -0.0001

Data Index: 351060 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1120. Min Act: -0.0001

Data Index: 457829 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1345284 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0964. Min Act: -0.0001

Data Index: 156566 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1115. Min Act: -0.0001

Data Index: 981935 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1307474 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1107. Min Act: -0.0001

Data Index: 8310 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1058. Min Act: -0.0001

Data Index: 466855 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1027. Min Act: -0.0001

Data Index: 583437 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1067. Min Act: -0.0001

Data Index: 115119 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1327066 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0922. Min Act: -0.0001

Data Index: 816821 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1226122 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1015. Min Act: -0.0001

Data Index: 881984 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1247869 (C4 (Web Text))

Max Activating Token Index: 947