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

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

Neuron 2053 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1173067 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1270. Min Act: -0.0000

Data Index: 82144 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1219. Min Act: -0.0000

Data Index: 114523 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1215. Min Act: -0.0000

Data Index: 542371 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1045. Min Act: -0.0000

Data Index: 995804 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1044. Min Act: -0.0000

Data Index: 194569 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1419645 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1052. Min Act: -0.0000

Data Index: 769982 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1024. Min Act: -0.0000

Data Index: 740328 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1073. Min Act: -0.0000

Data Index: 435143 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1038. Min Act: -0.0000

Data Index: 878412 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1233403 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1005. Min Act: -0.0000

Data Index: 270052 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0713. Min Act: -0.0000

Data Index: 18183 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0965. Min Act: -0.0000

Data Index: 452753 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1003. Min Act: -0.0000

Data Index: 583446 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1399269 (Python Code)

Max Activating Token Index: 498

Text #17

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0969. Min Act: -0.0000

Data Index: 92331 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1089888 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1338327 (C4 (Web Text))

Max Activating Token Index: 782