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

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

Neuron 3872 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1186721 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2582. Min Act: -0.0000

Data Index: 707777 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1143921 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2177. Min Act: -0.0001

Data Index: 1147976 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2196. Min Act: -0.0000

Data Index: 315841 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2323. Min Act: -0.0001

Data Index: 1335824 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1015236 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2066. Min Act: -0.0000

Data Index: 32815 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2001. Min Act: -0.0000

Data Index: 162592 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1931. Min Act: -0.0001

Data Index: 670385 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1987. Min Act: -0.0001

Data Index: 594609 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1974. Min Act: -0.0001

Data Index: 832717 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1900. Min Act: -0.0000

Data Index: 623403 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1874. Min Act: -0.0000

Data Index: 231269 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1876. Min Act: -0.0001

Data Index: 957760 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1850. Min Act: -0.0001

Data Index: 799936 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1302070 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1719. Min Act: -0.0000

Data Index: 532440 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1835. Min Act: -0.0000

Data Index: 191690 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1880. Min Act: -0.0001

Data Index: 304840 (C4 (Web Text))

Max Activating Token Index: 531