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

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

Neuron 631 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1378498 (Python Code)

Max Activating Token Index: 800

Text #1

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1496471 (Python Code)

Max Activating Token Index: 312

Text #2

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1317. Min Act: -0.0000

Data Index: 952241 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1260. Min Act: -0.0000

Data Index: 754874 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1535176 (Python Code)

Max Activating Token Index: 734

Text #5

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1418132 (Python Code)

Max Activating Token Index: 939

Text #6

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1226. Min Act: -0.0000

Data Index: 183786 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1366721 (Python Code)

Max Activating Token Index: 350

Text #8

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1608203 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1062. Min Act: -0.0000

Data Index: 948754 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1580738 (Python Code)

Max Activating Token Index: 981

Text #11

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1103. Min Act: -0.0000

Data Index: 378983 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1512053 (Python Code)

Max Activating Token Index: 847

Text #13

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1395623 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1100093 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1417622 (Python Code)

Max Activating Token Index: 961

Text #16

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1611202 (Python Code)

Max Activating Token Index: 276

Text #17

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.0947. Min Act: -0.0000

Data Index: 494928 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1653078 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1047. Min Act: -0.0000

Data Index: 985906 (C4 (Web Text))

Max Activating Token Index: 472