Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5601 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1039873 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0000

Data Index: 439919 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1483. Min Act: -0.0000

Data Index: 210004 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1470. Min Act: -0.0000

Data Index: 200282 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1378. Min Act: 0.0000

Data Index: 372661 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1293. Min Act: 0.0000

Data Index: 284780 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1261. Min Act: -0.0000

Data Index: 795785 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1235. Min Act: -0.0000

Data Index: 163076 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1264. Min Act: -0.0000

Data Index: 32108 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1292. Min Act: -0.0000

Data Index: 534772 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1136957 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1112160 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1091. Min Act: -0.0000

Data Index: 410650 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1129. Min Act: -0.0000

Data Index: 354099 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1279943 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1115. Min Act: -0.0000

Data Index: 938296 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1146. Min Act: -0.0000

Data Index: 622326 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1044. Min Act: -0.0000

Data Index: 498407 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1180144 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1144. Min Act: -0.0000

Data Index: 477880 (C4 (Web Text))

Max Activating Token Index: 285