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

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

Neuron 4874 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2980. Min Act: -0.0001

Data Index: 1560586 (Python Code)

Max Activating Token Index: 604

Text #1

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2765. Min Act: -0.0000

Data Index: 83090 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2519. Min Act: -0.0001

Data Index: 147080 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2836. Min Act: -0.0001

Data Index: 1514159 (Python Code)

Max Activating Token Index: 709

Text #4

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2278. Min Act: -0.0001

Data Index: 392761 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2597. Min Act: -0.0001

Data Index: 1495760 (Python Code)

Max Activating Token Index: 739

Text #6

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2080. Min Act: -0.0001

Data Index: 123165 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2469. Min Act: -0.0001

Data Index: 1055246 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2335. Min Act: -0.0001

Data Index: 1089810 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1373404 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1542269 (Python Code)

Max Activating Token Index: 550

Text #11

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2330. Min Act: -0.0001

Data Index: 1446648 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2320. Min Act: -0.0001

Data Index: 342309 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1537714 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1526161 (Python Code)

Max Activating Token Index: 74

Text #15

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1541569 (Python Code)

Max Activating Token Index: 164

Text #16

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2115. Min Act: -0.0001

Data Index: 914645 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2119. Min Act: -0.0001

Data Index: 435561 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2016. Min Act: -0.0001

Data Index: 1633775 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1546829 (Python Code)

Max Activating Token Index: 398