Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1821. Min Act: -0.0001

Data Index: 677650 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1679. Min Act: -0.0001

Data Index: 1359250 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1752. Min Act: -0.0001

Data Index: 1112607 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1300713 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1893. Min Act: -0.0001

Data Index: 1031751 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1591. Min Act: -0.0001

Data Index: 1124989 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1203333 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1057809 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1155156 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1565. Min Act: -0.0001

Data Index: 343043 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1287. Min Act: -0.0001

Data Index: 458387 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1325334 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1226. Min Act: -0.0001

Data Index: 96332 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1303. Min Act: -0.0001

Data Index: 262637 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1213. Min Act: -0.0001

Data Index: 768498 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1047729 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1321. Min Act: -0.0001

Data Index: 557793 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1082. Min Act: -0.0001

Data Index: 773425 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1204. Min Act: -0.0001

Data Index: 552621 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1412. Min Act: -0.0001

Data Index: 747829 (C4 (Web Text))

Max Activating Token Index: 657