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

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

Neuron 5388 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: 0.1858. Min Range: -0.1858

Max Act: 0.1714. Min Act: -0.0000

Data Index: 564447 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1069044 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1858. Min Act: -0.0000

Data Index: 27050 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1306362 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1552. Min Act: -0.0000

Data Index: 71358 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1584. Min Act: -0.0000

Data Index: 284108 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1393. Min Act: -0.0000

Data Index: 857075 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1304. Min Act: -0.0000

Data Index: 342272 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1148. Min Act: -0.0000

Data Index: 36778 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1068. Min Act: -0.0000

Data Index: 268385 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1080. Min Act: -0.0000

Data Index: 106990 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1140. Min Act: -0.0000

Data Index: 486487 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1091. Min Act: -0.0000

Data Index: 684416 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1164. Min Act: -0.0000

Data Index: 879808 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1044. Min Act: -0.0000

Data Index: 831590 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1618539 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1089. Min Act: -0.0000

Data Index: 650186 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1146403 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1027. Min Act: 0.0000

Data Index: 672118 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.1858. Min Range: -0.1858

Max Act: 0.1033. Min Act: 0.0000

Data Index: 75784 (C4 (Web Text))

Max Activating Token Index: 291