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

Dataset: The Pile

Neuron 30 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.8215. Min Act: -0.0000

Data Index: 522344 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.1126. Min Act: 0.0000

Data Index: 611039 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.5286. Min Act: -0.0000

Data Index: 663023 (The Pile)

Max Activating Token Index: 941

Text #3

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.2349. Min Act: -0.0000

Data Index: 232985 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.3711. Min Act: -0.0000

Data Index: 452968 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.1777. Min Act: -0.0000

Data Index: 1249642 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.1971. Min Act: -0.0000

Data Index: 46443 (The Pile)

Max Activating Token Index: 963

Text #7

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.3017. Min Act: -0.0000

Data Index: 265920 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.2817. Min Act: -0.0000

Data Index: 775994 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.2320. Min Act: -0.0000

Data Index: 486062 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.3817. Min Act: -0.0000

Data Index: 124490 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.3269. Min Act: -0.0000

Data Index: 1493065 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.0550. Min Act: 0.0000

Data Index: 282191 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.1941. Min Act: -0.0000

Data Index: 448380 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.1633. Min Act: -0.0000

Data Index: 1291341 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.2931. Min Act: 0.0000

Data Index: 703198 (The Pile)

Max Activating Token Index: 905

Text #16

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.2642. Min Act: -0.0000

Data Index: 926788 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 3.8215. Min Range: -3.8215

Max Act: 2.9541. Min Act: -0.0000

Data Index: 1244219 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 3.8215. Min Range: -3.8215

Max Act: 2.9650. Min Act: -0.0000

Data Index: 1683423 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 3.8215. Min Range: -3.8215

Max Act: 3.0998. Min Act: -0.0000

Data Index: 306677 (The Pile)

Max Activating Token Index: 946