Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5674 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1550. Min Act: -0.0001

Data Index: 77439 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1437. Min Act: -0.0001

Data Index: 586225 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1476. Min Act: -0.0001

Data Index: 202738 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1328. Min Act: -0.0001

Data Index: 544904 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1339. Min Act: -0.0001

Data Index: 945054 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1223. Min Act: -0.0001

Data Index: 737209 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.0991. Min Act: -0.0001

Data Index: 907087 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1012384 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1173. Min Act: -0.0001

Data Index: 338511 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1068. Min Act: -0.0001

Data Index: 487250 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1148. Min Act: -0.0001

Data Index: 963877 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1127. Min Act: -0.0001

Data Index: 624898 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1043. Min Act: -0.0001

Data Index: 207646 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1101. Min Act: -0.0001

Data Index: 122472 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1260708 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1016. Min Act: -0.0001

Data Index: 25829 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1183. Min Act: -0.0001

Data Index: 529516 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1186. Min Act: -0.0001

Data Index: 63850 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.0995. Min Act: -0.0001

Data Index: 280068 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1149296 (C4 (Web Text))

Max Activating Token Index: 592