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

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

Neuron 478 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2392. Min Act: -0.0000

Data Index: 89450 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2330. Min Act: -0.0001

Data Index: 838992 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2306. Min Act: -0.0000

Data Index: 239225 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2281. Min Act: -0.0000

Data Index: 609192 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2239. Min Act: -0.0000

Data Index: 899883 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1317329 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2204. Min Act: -0.0000

Data Index: 527409 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2100. Min Act: -0.0001

Data Index: 942507 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2150. Min Act: -0.0000

Data Index: 967562 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2065. Min Act: -0.0000

Data Index: 930820 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2119. Min Act: -0.0001

Data Index: 1096088 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1008685 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1088010 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2056. Min Act: -0.0000

Data Index: 532049 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2110. Min Act: -0.0000

Data Index: 17422 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2099. Min Act: -0.0000

Data Index: 557949 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1185292 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2092. Min Act: -0.0000

Data Index: 411190 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1145570 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1147726 (C4 (Web Text))

Max Activating Token Index: 913