Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1085 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1100. Min Act: -0.0005

Data Index: 995665 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1143. Min Act: -0.0005

Data Index: 221853 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1105. Min Act: -0.0005

Data Index: 624923 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1042. Min Act: -0.0005

Data Index: 818233 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1131. Min Act: -0.0005

Data Index: 7080 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1136. Min Act: -0.0005

Data Index: 1267511 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1047. Min Act: -0.0005

Data Index: 589169 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1076. Min Act: -0.0005

Data Index: 497868 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1101. Min Act: -0.0005

Data Index: 249422 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1028. Min Act: -0.0005

Data Index: 322071 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1020. Min Act: -0.0005

Data Index: 729157 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0992. Min Act: -0.0005

Data Index: 302378 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1028. Min Act: -0.0005

Data Index: 1087774 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1007. Min Act: -0.0005

Data Index: 1026907 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1037. Min Act: -0.0005

Data Index: 706719 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0983. Min Act: -0.0005

Data Index: 68418 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1018. Min Act: -0.0005

Data Index: 223433 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0971. Min Act: -0.0005

Data Index: 229794 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1031. Min Act: -0.0005

Data Index: 598872 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1017. Min Act: -0.0005

Data Index: 369091 (C4 (Web Text))

Max Activating Token Index: 41