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

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

Neuron 4071 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1522977 (Python Code)

Max Activating Token Index: 230

Text #1

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0796. Min Act: -0.0000

Data Index: 214376 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0794. Min Act: -0.0000

Data Index: 663772 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1178357 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0662. Min Act: -0.0000

Data Index: 139466 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1359648 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0606. Min Act: -0.0000

Data Index: 118262 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0668. Min Act: -0.0000

Data Index: 488819 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1227858 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0600. Min Act: -0.0000

Data Index: 508503 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1514467 (Python Code)

Max Activating Token Index: 1017

Text #11

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0590. Min Act: -0.0001

Data Index: 854302 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1550738 (Python Code)

Max Activating Token Index: 123

Text #13

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1285466 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0500. Min Act: -0.0000

Data Index: 491419 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1401037 (Python Code)

Max Activating Token Index: 102

Text #16

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0535. Min Act: -0.0000

Data Index: 976581 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1130078 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1298380 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1478669 (Python Code)

Max Activating Token Index: 595