Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4972 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5377. Min Range: -1.5377

Max Act: 1.1553. Min Act: -0.0000

Data Index: 1247510 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.5377. Min Range: -1.5377

Max Act: 1.5377. Min Act: -0.0000

Data Index: 112284 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.2063. Min Act: -0.0000

Data Index: 97690 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.4968. Min Act: -0.0000

Data Index: 598960 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1525089 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1028965 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1226. Min Act: -0.0000

Data Index: 367747 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1206288 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1606830 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1335404 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1423355 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1179. Min Act: -0.0000

Data Index: 108095 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1371746 (Python Code)

Max Activating Token Index: 754

Text #13

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1485719 (Python Code)

Max Activating Token Index: 276

Text #14

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.0981. Min Act: -0.0000

Data Index: 653849 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1418509 (Python Code)

Max Activating Token Index: 323

Text #16

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1371539 (Python Code)

Max Activating Token Index: 592

Text #17

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1146958 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1470234 (Python Code)

Max Activating Token Index: 551

Text #19

Max Range: 1.5377. Min Range: -1.5377

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1083276 (C4 (Web Text))

Max Activating Token Index: 649