Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4594 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1498. Min Act: -0.0001

Data Index: 317506 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1191688 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1392. Min Act: -0.0001

Data Index: 168968 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1252. Min Act: -0.0001

Data Index: 741188 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1164. Min Act: -0.0001

Data Index: 445838 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1245628 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1097987 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1104. Min Act: -0.0001

Data Index: 377279 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1129. Min Act: -0.0001

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1138. Min Act: -0.0001

Data Index: 675944 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1149. Min Act: -0.0001

Data Index: 224522 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1146. Min Act: -0.0001

Data Index: 189981 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1334904 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1121. Min Act: -0.0001

Data Index: 174098 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1244928 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1148. Min Act: -0.0001

Data Index: 993603 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1050. Min Act: -0.0001

Data Index: 643860 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1055499 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1021. Min Act: -0.0001

Data Index: 270532 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1052. Min Act: -0.0001

Data Index: 49714 (C4 (Web Text))

Max Activating Token Index: 321