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

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

Neuron 105 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: 0.7206. Min Range: -0.7206

Max Act: 0.6981. Min Act: -0.0000

Data Index: 265718 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1420194 (Python Code)

Max Activating Token Index: 952

Text #2

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6597. Min Act: -0.0000

Data Index: 543558 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6496. Min Act: -0.0000

Data Index: 553556 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6666. Min Act: -0.0000

Data Index: 753893 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5716. Min Act: -0.0000

Data Index: 562515 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1432496 (Python Code)

Max Activating Token Index: 403

Text #7

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1514966 (Python Code)

Max Activating Token Index: 656

Text #8

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6279. Min Act: -0.0000

Data Index: 66004 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1573269 (Python Code)

Max Activating Token Index: 875

Text #10

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5989. Min Act: -0.0000

Data Index: 168871 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1594392 (Python Code)

Max Activating Token Index: 733

Text #12

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1456552 (Python Code)

Max Activating Token Index: 847

Text #13

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1597563 (Python Code)

Max Activating Token Index: 979

Text #14

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5775. Min Act: -0.0000

Data Index: 935503 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1394507 (Python Code)

Max Activating Token Index: 495

Text #16

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1436583 (Python Code)

Max Activating Token Index: 567

Text #17

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5672. Min Act: -0.0000

Data Index: 270298 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5622. Min Act: -0.0000

Data Index: 572502 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1642501 (Python Code)

Max Activating Token Index: 192