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

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

Neuron 3483 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1615844 (Python Code)

Max Activating Token Index: 560

Text #1

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1195253 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1591239 (Python Code)

Max Activating Token Index: 630

Text #3

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1234377 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1350614 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1287. Min Act: -0.0000

Data Index: 749112 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1410717 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1006482 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1168. Min Act: -0.0000

Data Index: 468623 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1571663 (Python Code)

Max Activating Token Index: 503

Text #10

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1269. Min Act: -0.0000

Data Index: 978855 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1118. Min Act: -0.0000

Data Index: 950270 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1045. Min Act: -0.0000

Data Index: 40761 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1507210 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1148. Min Act: -0.0000

Data Index: 351273 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1343. Min Act: -0.0000

Data Index: 592203 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1126. Min Act: -0.0000

Data Index: 219774 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1056. Min Act: -0.0000

Data Index: 801366 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1079. Min Act: -0.0000

Data Index: 778352 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1114. Min Act: -0.0000

Data Index: 784995 (C4 (Web Text))

Max Activating Token Index: 188