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

Dataset: The Pile

Neuron 4079 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.6557. Min Act: -0.0000

Data Index: 938784 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2572. Min Act: -0.0000

Data Index: 201070 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1448797 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1159766 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1827. Min Act: -0.0000

Data Index: 904412 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2567. Min Act: -0.0000

Data Index: 1241158 (The Pile)

Max Activating Token Index: 839

Text #6

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1975. Min Act: -0.0000

Data Index: 1518325 (The Pile)

Max Activating Token Index: 170

Text #7

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1211213 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1467108 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 1.6557. Min Range: -1.6557

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1447292 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 1.6557. Min Range: -1.6557

Max Act: 0.9647. Min Act: -0.0000

Data Index: 359520 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1374. Min Act: -0.0000

Data Index: 346589 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 1.6557. Min Range: -1.6557

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1329756 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.0159. Min Act: -0.0000

Data Index: 749192 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 1.6557. Min Range: -1.6557

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1068763 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 1.6557. Min Range: -1.6557

Max Act: 0.9877. Min Act: -0.0000

Data Index: 447316 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 1.6557. Min Range: -1.6557

Max Act: 0.9310. Min Act: -0.0000

Data Index: 399009 (The Pile)

Max Activating Token Index: 649

Text #17

Max Range: 1.6557. Min Range: -1.6557

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1420497 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.0688. Min Act: -0.0000

Data Index: 124427 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.0467. Min Act: -0.0000

Data Index: 301206 (The Pile)

Max Activating Token Index: 904