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

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

Neuron 4675 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1469. Min Act: -0.0001

Data Index: 673014 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1264. Min Act: -0.0001

Data Index: 400960 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1209. Min Act: -0.0001

Data Index: 488631 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1212. Min Act: -0.0001

Data Index: 736033 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1136. Min Act: -0.0001

Data Index: 107743 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1167. Min Act: -0.0001

Data Index: 75455 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1208. Min Act: -0.0001

Data Index: 389257 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1310746 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1025168 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1179978 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1163. Min Act: -0.0001

Data Index: 192958 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1068. Min Act: -0.0001

Data Index: 333152 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1101564 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1081686 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1355973 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1178798 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1084. Min Act: -0.0001

Data Index: 193069 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1095. Min Act: -0.0001

Data Index: 187677 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1182. Min Act: -0.0001

Data Index: 968911 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1082. Min Act: -0.0001

Data Index: 286981 (C4 (Web Text))

Max Activating Token Index: 23