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

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

Neuron 862 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.7475. Min Act: -0.0000

Data Index: 643245 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1283938 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.7066. Min Act: -0.0001

Data Index: 1564592 (Python Code)

Max Activating Token Index: 181

Text #3

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6985. Min Act: -0.0000

Data Index: 976605 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.7203. Min Act: -0.0001

Data Index: 1444099 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1459969 (Python Code)

Max Activating Token Index: 585

Text #6

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1372634 (Python Code)

Max Activating Token Index: 331

Text #7

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1626555 (Python Code)

Max Activating Token Index: 733

Text #8

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1473428 (Python Code)

Max Activating Token Index: 146

Text #9

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1055443 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5820. Min Act: -0.0001

Data Index: 1636513 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5941. Min Act: -0.0000

Data Index: 894735 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1455185 (Python Code)

Max Activating Token Index: 716

Text #13

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5950. Min Act: -0.0000

Data Index: 806533 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1459715 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1085835 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6153. Min Act: -0.0000

Data Index: 600050 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1339274 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5705. Min Act: -0.0000

Data Index: 558346 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6087. Min Act: -0.0000

Data Index: 155113 (C4 (Web Text))

Max Activating Token Index: 599