Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 617 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1821. Min Act: -0.0002

Data Index: 1294161 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1842. Min Act: -0.0002

Data Index: 1328306 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1783. Min Act: -0.0002

Data Index: 976679 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1763. Min Act: -0.0002

Data Index: 32269 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1660. Min Act: -0.0002

Data Index: 236147 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1617. Min Act: -0.0002

Data Index: 223952 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1583. Min Act: -0.0002

Data Index: 834812 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1573. Min Act: -0.0002

Data Index: 1139034 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1609. Min Act: -0.0002

Data Index: 266446 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1560. Min Act: -0.0002

Data Index: 664049 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1519. Min Act: -0.0002

Data Index: 992412 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1518. Min Act: -0.0002

Data Index: 831380 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1478. Min Act: -0.0002

Data Index: 830838 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1447. Min Act: -0.0002

Data Index: 337090 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1442. Min Act: -0.0002

Data Index: 806648 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1447. Min Act: -0.0002

Data Index: 463592 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1425. Min Act: -0.0002

Data Index: 1030233 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1426. Min Act: -0.0002

Data Index: 520411 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1416. Min Act: -0.0002

Data Index: 131336 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1438. Min Act: -0.0002

Data Index: 919366 (C4 (Web Text))

Max Activating Token Index: 828