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

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

Neuron 3240 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1378514 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1364750 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1406638 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1244. Min Act: -0.0001

Data Index: 583358 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1611189 (Python Code)

Max Activating Token Index: 701

Text #5

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1389045 (Python Code)

Max Activating Token Index: 471

Text #6

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1614739 (Python Code)

Max Activating Token Index: 550

Text #7

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1619935 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1404902 (Python Code)

Max Activating Token Index: 508

Text #9

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1563108 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1515422 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1639088 (Python Code)

Max Activating Token Index: 319

Text #12

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1228559 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1621602 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1471985 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1129. Min Act: -0.0001

Data Index: 48391 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1104. Min Act: -0.0001

Data Index: 351685 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1372251 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1540056 (Python Code)

Max Activating Token Index: 226

Text #19

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1595801 (Python Code)

Max Activating Token Index: 715