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

Dataset: The Pile

Neuron 294 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.7407. Min Act: -0.0000

Data Index: 425787 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.6601. Min Act: -0.0000

Data Index: 1420130 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1696. Min Act: -0.0000

Data Index: 1472982 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0410. Min Act: -0.0000

Data Index: 288547 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1133167 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9894. Min Act: -0.0000

Data Index: 1006845 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9764. Min Act: 0.0000

Data Index: 507627 (The Pile)

Max Activating Token Index: 702

Text #7

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9137. Min Act: -0.0000

Data Index: 339863 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9192. Min Act: -0.0000

Data Index: 288090 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1383030 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.7606. Min Act: -0.0000

Data Index: 889445 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9464. Min Act: 0.0000

Data Index: 1196182 (The Pile)

Max Activating Token Index: 880

Text #12

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.8398. Min Act: -0.0000

Data Index: 354467 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.8384. Min Act: -0.0000

Data Index: 956452 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1443507 (The Pile)

Max Activating Token Index: 771

Text #15

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1564031 (The Pile)

Max Activating Token Index: 664

Text #16

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.8630. Min Act: 0.0000

Data Index: 710537 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9043. Min Act: -0.0000

Data Index: 535686 (The Pile)

Max Activating Token Index: 866

Text #18

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1434084 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1054270 (The Pile)

Max Activating Token Index: 693