Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 394 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0826. Min Range: -1.0826

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1967265 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 1.0826. Min Range: -1.0826

Max Act: 1.0283. Min Act: -0.0000

Data Index: 467380 (The Pile)

Max Activating Token Index: 652

Text #2

Max Range: 1.0826. Min Range: -1.0826

Max Act: 1.0217. Min Act: -0.0000

Data Index: 1857639 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1151721 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1650404 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9419. Min Act: -0.0000

Data Index: 628359 (The Pile)

Max Activating Token Index: 892

Text #6

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9145. Min Act: -0.0000

Data Index: 856569 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 1.0826. Min Range: -1.0826

Max Act: 1.0057. Min Act: -0.0000

Data Index: 1852024 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9916. Min Act: -0.0000

Data Index: 773576 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1286489 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1528406 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8966. Min Act: -0.0000

Data Index: 613293 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1650047 (The Pile)

Max Activating Token Index: 558

Text #13

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1610557 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9045. Min Act: -0.0000

Data Index: 352773 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1698499 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1130694 (The Pile)

Max Activating Token Index: 719

Text #17

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1679656 (The Pile)

Max Activating Token Index: 877

Text #18

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8500. Min Act: -0.0000

Data Index: 774611 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1569781 (The Pile)

Max Activating Token Index: 777