Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1374 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2623. Min Act: -0.0001

Data Index: 301241 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2244. Min Act: -0.0001

Data Index: 368711 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1082751 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2201. Min Act: -0.0001

Data Index: 594042 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2096. Min Act: -0.0001

Data Index: 708206 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2074. Min Act: -0.0001

Data Index: 499261 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2147. Min Act: -0.0001

Data Index: 826329 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2071. Min Act: -0.0001

Data Index: 744244 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2210. Min Act: -0.0001

Data Index: 631820 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2034. Min Act: -0.0001

Data Index: 78461 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2031. Min Act: -0.0001

Data Index: 163205 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2027. Min Act: -0.0001

Data Index: 862570 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2026. Min Act: -0.0001

Data Index: 148345 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1990. Min Act: -0.0001

Data Index: 1107512 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1903. Min Act: -0.0001

Data Index: 1192156 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1965. Min Act: -0.0001

Data Index: 298725 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1954. Min Act: -0.0001

Data Index: 382213 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1913. Min Act: -0.0001

Data Index: 251039 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1327357 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1970. Min Act: -0.0001

Data Index: 960491 (C4 (Web Text))

Max Activating Token Index: 448