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

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

Neuron 1701 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1559. Min Act: -0.0000

Data Index: 823510 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1225451 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1504. Min Act: -0.0000

Data Index: 131990 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1179353 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1484. Min Act: -0.0000

Data Index: 774184 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1295. Min Act: -0.0000

Data Index: 1026383 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1598597 (Python Code)

Max Activating Token Index: 335

Text #7

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1124774 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1100. Min Act: -0.0000

Data Index: 299767 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1168. Min Act: -0.0000

Data Index: 760213 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1167. Min Act: -0.0000

Data Index: 666307 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1158419 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1221. Min Act: -0.0000

Data Index: 470505 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1390544 (Python Code)

Max Activating Token Index: 573

Text #14

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1191120 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1092877 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1114. Min Act: -0.0001

Data Index: 215545 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1078. Min Act: -0.0000

Data Index: 377565 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1234557 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1049. Min Act: -0.0000

Data Index: 50932 (C4 (Web Text))

Max Activating Token Index: 282