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

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

Neuron 2650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0001

Data Index: 697851 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1092952 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1004284 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0739. Min Act: -0.0000

Data Index: 199333 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0642. Min Act: -0.0000

Data Index: 473942 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0684. Min Act: -0.0001

Data Index: 104174 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0667. Min Act: -0.0000

Data Index: 541132 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0601. Min Act: -0.0001

Data Index: 580290 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0621. Min Act: -0.0000

Data Index: 129298 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0644. Min Act: -0.0000

Data Index: 554752 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0554. Min Act: -0.0000

Data Index: 67764 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1309147 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0600. Min Act: -0.0001

Data Index: 603725 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0584. Min Act: -0.0000

Data Index: 570692 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0569. Min Act: -0.0000

Data Index: 904335 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0533. Min Act: -0.0000

Data Index: 534465 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0517. Min Act: -0.0000

Data Index: 14371 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0577. Min Act: -0.0001

Data Index: 539120 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0501. Min Act: -0.0000

Data Index: 351820 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0527. Min Act: -0.0000

Data Index: 1355966 (C4 (Web Text))

Max Activating Token Index: 8