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

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

Neuron 782 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1056015 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1353371 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1272. Min Act: -0.0000

Data Index: 236595 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1272. Min Act: -0.0000

Data Index: 724482 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1176. Min Act: -0.0000

Data Index: 576085 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1242. Min Act: -0.0000

Data Index: 151528 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1621964 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1117053 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1431033 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1108. Min Act: -0.0000

Data Index: 426528 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1556452 (Python Code)

Max Activating Token Index: 403

Text #11

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1131. Min Act: -0.0000

Data Index: 464600 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1130. Min Act: -0.0000

Data Index: 155549 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1531473 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1148615 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1019. Min Act: -0.0000

Data Index: 841547 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1230634 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1090. Min Act: -0.0000

Data Index: 807275 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1506899 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1516422 (Python Code)

Max Activating Token Index: 438