Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1691 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1119. Min Act: -0.0000

Data Index: 1356898 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1635. Min Act: -0.0000

Data Index: 41121 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9023. Min Act: -0.0001

Data Index: 865645 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9833. Min Act: -0.0000

Data Index: 1226330 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1028834 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8563. Min Act: -0.0000

Data Index: 298684 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7781. Min Act: -0.0000

Data Index: 976225 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8207. Min Act: -0.0000

Data Index: 480924 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1055623 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1254476 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7568. Min Act: -0.0001

Data Index: 494397 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7173. Min Act: -0.0001

Data Index: 931822 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1352158 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1295762 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7287. Min Act: -0.0001

Data Index: 61755 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7293. Min Act: -0.0000

Data Index: 743321 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7294. Min Act: -0.0001

Data Index: 155316 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7512. Min Act: -0.0000

Data Index: 243513 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7227. Min Act: -0.0001

Data Index: 508403 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7193. Min Act: -0.0000

Data Index: 378388 (C4 (Web Text))

Max Activating Token Index: 747