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

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

Neuron 2399 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: 0.1550. Min Range: -0.1550

Max Act: 0.1550. Min Act: -0.0001

Data Index: 740535 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1540. Min Act: -0.0001

Data Index: 524157 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1328. Min Act: -0.0000

Data Index: 149859 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1253. Min Act: -0.0001

Data Index: 758253 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1325571 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1171. Min Act: -0.0001

Data Index: 578997 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1225580 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1186. Min Act: -0.0001

Data Index: 869761 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1139. Min Act: -0.0001

Data Index: 744909 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1126. Min Act: -0.0001

Data Index: 516330 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1112. Min Act: -0.0001

Data Index: 715528 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1105. Min Act: -0.0000

Data Index: 415691 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1164. Min Act: -0.0001

Data Index: 605312 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1113. Min Act: -0.0001

Data Index: 549135 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1114. Min Act: -0.0001

Data Index: 511045 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1149372 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1057. Min Act: -0.0001

Data Index: 490072 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1103853 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1096. Min Act: -0.0001

Data Index: 565796 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1114. Min Act: -0.0001

Data Index: 998586 (C4 (Web Text))

Max Activating Token Index: 892