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

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

Neuron 1730 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.6969. Min Act: -0.0000

Data Index: 868038 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.3145. Min Act: -0.0000

Data Index: 223973 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.3805. Min Act: -0.0000

Data Index: 918711 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.1333. Min Act: -0.0000

Data Index: 387826 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.0735. Min Act: -0.0000

Data Index: 202202 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.0031. Min Act: -0.0000

Data Index: 260116 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.0437. Min Act: -0.0000

Data Index: 477714 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.9282. Min Act: -0.0000

Data Index: 59617 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.8282. Min Act: -0.0000

Data Index: 127171 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.8776. Min Act: -0.0000

Data Index: 33272 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1057338 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1206026 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1459654 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1108779 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.7917. Min Act: -0.0000

Data Index: 313020 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1639658 (Python Code)

Max Activating Token Index: 617

Text #16

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.7624. Min Act: -0.0000

Data Index: 20149 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1345643 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.7604. Min Act: -0.0000

Data Index: 833525 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 1.6969. Min Range: -1.6969

Max Act: 0.7374. Min Act: -0.0000

Data Index: 219802 (C4 (Web Text))

Max Activating Token Index: 36