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

Dataset: The Pile

Neuron 957 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: 3.8321. Min Range: -3.8321

Max Act: 3.8321. Min Act: -0.0000

Data Index: 1434490 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.7797. Min Act: -0.0000

Data Index: 1983386 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.7589. Min Act: -0.0000

Data Index: 1786205 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.4063. Min Act: -0.0000

Data Index: 39363 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5718. Min Act: -0.0000

Data Index: 908699 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5428. Min Act: -0.0000

Data Index: 996604 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.4639. Min Act: -0.0000

Data Index: 1081439 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.3898. Min Act: -0.0000

Data Index: 133458 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.6893. Min Act: -0.0000

Data Index: 1978019 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5648. Min Act: -0.0000

Data Index: 1683613 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5256. Min Act: -0.0000

Data Index: 1865741 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.4678. Min Act: -0.0000

Data Index: 1603518 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.4648. Min Act: -0.0000

Data Index: 1309748 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.2885. Min Act: -0.0000

Data Index: 602767 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.2731. Min Act: -0.0000

Data Index: 1885520 (The Pile)

Max Activating Token Index: 892

Text #15

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.4011. Min Act: -0.0000

Data Index: 181416 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.2277. Min Act: -0.0000

Data Index: 808810 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.2216. Min Act: -0.0000

Data Index: 372483 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.3677. Min Act: -0.0000

Data Index: 923767 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.3461. Min Act: -0.0000

Data Index: 1037981 (The Pile)

Max Activating Token Index: 728