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

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

Neuron 4233 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1749. Min Act: -0.0002

Data Index: 666713 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1239. Min Act: -0.0002

Data Index: 843413 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1281. Min Act: -0.0002

Data Index: 229152 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1181. Min Act: -0.0002

Data Index: 60494 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1182. Min Act: -0.0002

Data Index: 989027 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1104. Min Act: -0.0002

Data Index: 662271 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1104. Min Act: -0.0002

Data Index: 163784 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1174. Min Act: -0.0002

Data Index: 443069 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1273905 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1099. Min Act: -0.0002

Data Index: 825229 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1118. Min Act: -0.0002

Data Index: 1206908 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1051. Min Act: -0.0002

Data Index: 842163 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1081097 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1084. Min Act: -0.0002

Data Index: 90638 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1061. Min Act: -0.0002

Data Index: 8806 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0891. Min Act: -0.0002

Data Index: 919610 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1109. Min Act: -0.0002

Data Index: 704102 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0943. Min Act: -0.0002

Data Index: 992196 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0887. Min Act: -0.0002

Data Index: 454293 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0953. Min Act: -0.0002

Data Index: 311106 (C4 (Web Text))

Max Activating Token Index: 358