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

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

Neuron 1453 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2625. Min Act: -0.0001

Data Index: 1204975 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2407. Min Act: -0.0001

Data Index: 189898 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2372. Min Act: -0.0001

Data Index: 900194 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2592. Min Act: -0.0001

Data Index: 953347 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2225. Min Act: -0.0001

Data Index: 546578 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2329. Min Act: -0.0001

Data Index: 250227 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2126. Min Act: -0.0001

Data Index: 443053 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2199. Min Act: -0.0001

Data Index: 1269355 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2386. Min Act: -0.0001

Data Index: 837871 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2173. Min Act: -0.0001

Data Index: 578423 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2093. Min Act: -0.0001

Data Index: 342768 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2119. Min Act: -0.0001

Data Index: 1110175 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2058. Min Act: -0.0001

Data Index: 455999 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1166708 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1828. Min Act: -0.0001

Data Index: 157897 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1870. Min Act: -0.0001

Data Index: 404927 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1926. Min Act: -0.0001

Data Index: 154817 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1763. Min Act: -0.0001

Data Index: 622888 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1816. Min Act: -0.0001

Data Index: 234978 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1663. Min Act: -0.0001

Data Index: 1257809 (C4 (Web Text))

Max Activating Token Index: 298