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

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

Neuron 4456 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1513500 (Python Code)

Max Activating Token Index: 631

Text #1

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1497504 (Python Code)

Max Activating Token Index: 516

Text #2

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1425303 (Python Code)

Max Activating Token Index: 417

Text #3

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1435438 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1419054 (Python Code)

Max Activating Token Index: 427

Text #5

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1411835 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1374512 (Python Code)

Max Activating Token Index: 100

Text #7

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1129356 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1634213 (Python Code)

Max Activating Token Index: 582

Text #9

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1623053 (Python Code)

Max Activating Token Index: 627

Text #10

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1270433 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1522297 (Python Code)

Max Activating Token Index: 239

Text #12

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1396827 (Python Code)

Max Activating Token Index: 207

Text #13

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1515102 (Python Code)

Max Activating Token Index: 693

Text #14

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1489302 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1479763 (Python Code)

Max Activating Token Index: 831

Text #16

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1647177 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1554906 (Python Code)

Max Activating Token Index: 154

Text #18

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1510392 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1530234 (Python Code)

Max Activating Token Index: 158