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

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

Neuron 134 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: 0.1498. Min Range: -0.1498

Max Act: 0.1498. Min Act: -0.0001

Data Index: 759492 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1326. Min Act: -0.0001

Data Index: 489684 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1281. Min Act: -0.0001

Data Index: 497178 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1131705 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1279. Min Act: -0.0001

Data Index: 742768 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1174. Min Act: -0.0001

Data Index: 135903 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1250887 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1146. Min Act: -0.0001

Data Index: 394274 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1156. Min Act: -0.0001

Data Index: 560837 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1158. Min Act: -0.0001

Data Index: 795667 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1115. Min Act: -0.0001

Data Index: 1210022 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1129. Min Act: -0.0001

Data Index: 332056 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1157. Min Act: -0.0001

Data Index: 836994 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1100. Min Act: -0.0001

Data Index: 160584 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1168. Min Act: -0.0001

Data Index: 170263 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1049. Min Act: -0.0001

Data Index: 814130 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1082. Min Act: -0.0001

Data Index: 550676 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1233497 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1146. Min Act: -0.0001

Data Index: 793687 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1013. Min Act: -0.0001

Data Index: 578208 (C4 (Web Text))

Max Activating Token Index: 620