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

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

Neuron 2029 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: 0.1566. Min Range: -0.1566

Max Act: 0.1566. Min Act: -0.0001

Data Index: 939418 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1317. Min Act: -0.0001

Data Index: 850055 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1330. Min Act: -0.0001

Data Index: 566098 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1209418 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1126106 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1366. Min Act: -0.0001

Data Index: 944418 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1357. Min Act: -0.0001

Data Index: 223587 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1049. Min Act: -0.0001

Data Index: 434238 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1247. Min Act: -0.0001

Data Index: 725442 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1161. Min Act: -0.0001

Data Index: 798469 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1036. Min Act: -0.0001

Data Index: 18615 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1162. Min Act: -0.0001

Data Index: 574733 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1073371 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1059. Min Act: -0.0001

Data Index: 317064 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1171. Min Act: -0.0001

Data Index: 702743 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1109. Min Act: -0.0001

Data Index: 730954 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1121. Min Act: -0.0001

Data Index: 982463 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1047812 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1063. Min Act: -0.0001

Data Index: 775919 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1145. Min Act: -0.0001

Data Index: 834925 (C4 (Web Text))

Max Activating Token Index: 93