Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1080 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.2035. Min Act: -0.0001

Data Index: 57992 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.2005. Min Act: -0.0001

Data Index: 891841 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1844. Min Act: -0.0001

Data Index: 1094055 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1293986 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1562. Min Act: -0.0001

Data Index: 662089 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1583. Min Act: -0.0001

Data Index: 1331239 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1512. Min Act: -0.0001

Data Index: 527373 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1625147 (Python Code)

Max Activating Token Index: 404

Text #8

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1317. Min Act: -0.0001

Data Index: 47565 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1446965 (Python Code)

Max Activating Token Index: 859

Text #10

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1293. Min Act: -0.0001

Data Index: 638194 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1499216 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1652213 (Python Code)

Max Activating Token Index: 635

Text #13

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1461. Min Act: -0.0001

Data Index: 318914 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1442252 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1405. Min Act: -0.0001

Data Index: 1254376 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1611955 (Python Code)

Max Activating Token Index: 301

Text #17

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1495. Min Act: -0.0001

Data Index: 1535684 (Python Code)

Max Activating Token Index: 670

Text #18

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1392. Min Act: -0.0001

Data Index: 364173 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1421. Min Act: -0.0001

Data Index: 1451342 (Python Code)

Max Activating Token Index: 93