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

Dataset: The Pile

Neuron 391 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: 1.3515. Min Range: -1.3515

Max Act: 1.3515. Min Act: -0.0000

Data Index: 170099 (The Pile)

Max Activating Token Index: 993

Text #1

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0512. Min Act: -0.0000

Data Index: 466403 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0165. Min Act: 0.0000

Data Index: 1616120 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1383783 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0081. Min Act: -0.0000

Data Index: 409172 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1817940 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9456. Min Act: -0.0000

Data Index: 1049609 (The Pile)

Max Activating Token Index: 875

Text #7

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9303. Min Act: -0.0000

Data Index: 55464 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9189. Min Act: -0.0000

Data Index: 411225 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8126. Min Act: -0.0000

Data Index: 23008 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9695. Min Act: -0.0000

Data Index: 279619 (The Pile)

Max Activating Token Index: 903

Text #11

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1195588 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1448847 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1886527 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8947. Min Act: -0.0000

Data Index: 108525 (The Pile)

Max Activating Token Index: 412

Text #15

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8383. Min Act: -0.0000

Data Index: 535672 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1294847 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1705088 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1334541 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8733. Min Act: 0.0000

Data Index: 486499 (The Pile)

Max Activating Token Index: 361