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

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

Neuron 2571 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1430. Min Act: -0.0001

Data Index: 912365 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1350. Min Act: -0.0002

Data Index: 1319933 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1292. Min Act: -0.0001

Data Index: 990407 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1284. Min Act: -0.0001

Data Index: 753195 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1238. Min Act: -0.0001

Data Index: 627881 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1267. Min Act: -0.0002

Data Index: 454868 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1236. Min Act: -0.0001

Data Index: 173083 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1167. Min Act: -0.0001

Data Index: 586944 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1196. Min Act: -0.0002

Data Index: 684877 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1168. Min Act: -0.0002

Data Index: 1152812 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1098181 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1072. Min Act: -0.0002

Data Index: 535535 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1253. Min Act: -0.0002

Data Index: 485148 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1134709 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1093985 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0979. Min Act: -0.0001

Data Index: 853860 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1052. Min Act: -0.0001

Data Index: 558175 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1198704 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1086. Min Act: -0.0002

Data Index: 970275 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1038. Min Act: -0.0002

Data Index: 575453 (C4 (Web Text))

Max Activating Token Index: 245