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

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

Neuron 2272 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2632. Min Act: -0.0001

Data Index: 1350142 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1287276 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2138. Min Act: -0.0001

Data Index: 1125831 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2288. Min Act: -0.0001

Data Index: 1286795 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2184. Min Act: -0.0001

Data Index: 799799 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2188. Min Act: -0.0001

Data Index: 1115553 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1857. Min Act: -0.0001

Data Index: 374396 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2022. Min Act: -0.0001

Data Index: 422839 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2009. Min Act: -0.0001

Data Index: 140563 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2116. Min Act: -0.0001

Data Index: 58482 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1300078 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2034. Min Act: -0.0001

Data Index: 232031 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1945. Min Act: -0.0001

Data Index: 534979 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1825. Min Act: -0.0001

Data Index: 844286 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1948. Min Act: -0.0001

Data Index: 658021 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1906. Min Act: -0.0001

Data Index: 855691 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1207134 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1907. Min Act: -0.0001

Data Index: 722843 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2054. Min Act: -0.0001

Data Index: 1327578 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1871. Min Act: -0.0001

Data Index: 607656 (C4 (Web Text))

Max Activating Token Index: 318