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

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

Neuron 3989 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1483. Min Act: -0.0000

Data Index: 235353 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1479. Min Act: -0.0000

Data Index: 641520 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1137. Min Act: -0.0000

Data Index: 875799 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1161. Min Act: -0.0000

Data Index: 573359 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1053. Min Act: -0.0000

Data Index: 726652 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1085. Min Act: -0.0000

Data Index: 423633 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.0966. Min Act: -0.0000

Data Index: 382821 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1057. Min Act: -0.0000

Data Index: 72927 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1012. Min Act: -0.0000

Data Index: 838914 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.0971. Min Act: -0.0000

Data Index: 1338943 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1283212 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.0959. Min Act: -0.0000

Data Index: 644624 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1348405 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.0929. Min Act: -0.0000

Data Index: 27323 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1118617 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1112581 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.0817. Min Act: -0.0000

Data Index: 837472 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1271927 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.0930. Min Act: -0.0000

Data Index: 308644 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1046. Min Act: -0.0000

Data Index: 409582 (C4 (Web Text))

Max Activating Token Index: 1019