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

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

Neuron 1388 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: 0.1610. Min Range: -0.1610

Max Act: 0.1610. Min Act: -0.0002

Data Index: 110123 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1606. Min Act: -0.0002

Data Index: 342467 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1585. Min Act: -0.0002

Data Index: 1204857 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1195897 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1501. Min Act: -0.0002

Data Index: 302239 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1299954 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1303. Min Act: -0.0002

Data Index: 40213 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1160. Min Act: -0.0002

Data Index: 882412 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1218. Min Act: -0.0002

Data Index: 876086 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1294754 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1163. Min Act: -0.0002

Data Index: 687288 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1160. Min Act: -0.0002

Data Index: 746319 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1134. Min Act: -0.0002

Data Index: 525827 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1137. Min Act: -0.0002

Data Index: 554465 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1112. Min Act: -0.0002

Data Index: 820077 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1066. Min Act: -0.0002

Data Index: 165800 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1037454 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1073. Min Act: -0.0002

Data Index: 77113 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1213. Min Act: -0.0002

Data Index: 785470 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1135588 (C4 (Web Text))

Max Activating Token Index: 670