Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 230 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1214569 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1449. Min Act: -0.0001

Data Index: 611818 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1493. Min Act: -0.0000

Data Index: 160800 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1449. Min Act: -0.0000

Data Index: 562541 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1427. Min Act: -0.0000

Data Index: 208841 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1315. Min Act: -0.0000

Data Index: 877389 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1394. Min Act: -0.0000

Data Index: 346134 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1237. Min Act: -0.0000

Data Index: 586015 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1125. Min Act: -0.0000

Data Index: 386218 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1189. Min Act: -0.0001

Data Index: 274300 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1133. Min Act: -0.0000

Data Index: 486489 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1027. Min Act: -0.0000

Data Index: 649037 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1147. Min Act: -0.0000

Data Index: 638757 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1108. Min Act: -0.0000

Data Index: 959069 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1133. Min Act: -0.0001

Data Index: 732997 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1319958 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1118. Min Act: -0.0000

Data Index: 275767 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1127. Min Act: 0.0000

Data Index: 1099485 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1107. Min Act: -0.0000

Data Index: 349274 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1054. Min Act: 0.0001

Data Index: 234626 (C4 (Web Text))

Max Activating Token Index: 547