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

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

Neuron 5058 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.4666. Min Act: -0.0001

Data Index: 1145793 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3163. Min Act: -0.0001

Data Index: 996436 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2299. Min Act: -0.0001

Data Index: 523853 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2198. Min Act: -0.0000

Data Index: 550901 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2864. Min Act: -0.0001

Data Index: 1258083 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1396. Min Act: -0.0000

Data Index: 551677 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1335369 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1788. Min Act: -0.0001

Data Index: 209499 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1105. Min Act: -0.0001

Data Index: 1207471 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1573. Min Act: -0.0001

Data Index: 1163799 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1284. Min Act: -0.0000

Data Index: 313174 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1264. Min Act: -0.0001

Data Index: 128837 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1608. Min Act: -0.0000

Data Index: 533770 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1185. Min Act: -0.0001

Data Index: 645901 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1181. Min Act: -0.0001

Data Index: 480725 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.0629. Min Act: -0.0000

Data Index: 600880 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1043. Min Act: -0.0000

Data Index: 915651 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1226278 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1649. Min Act: -0.0000

Data Index: 778772 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.0452. Min Act: -0.0001

Data Index: 1145614 (C4 (Web Text))

Max Activating Token Index: 848