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

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

Neuron 4023 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2597. Min Act: -0.0000

Data Index: 257412 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2574. Min Act: -0.0000

Data Index: 458727 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1194727 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2249. Min Act: -0.0000

Data Index: 240432 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1093727 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1966. Min Act: -0.0000

Data Index: 479618 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1580060 (Python Code)

Max Activating Token Index: 466

Text #7

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2007. Min Act: -0.0000

Data Index: 942719 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1639748 (Python Code)

Max Activating Token Index: 410

Text #9

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2003. Min Act: -0.0000

Data Index: 279911 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1161596 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1329860 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1988. Min Act: -0.0000

Data Index: 716378 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1917. Min Act: -0.0000

Data Index: 790130 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1957. Min Act: -0.0000

Data Index: 150801 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1805. Min Act: -0.0000

Data Index: 414147 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1878. Min Act: -0.0000

Data Index: 417991 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1656422 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1008341 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1789. Min Act: -0.0000

Data Index: 990671 (C4 (Web Text))

Max Activating Token Index: 365