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

Dataset: The Pile

Neuron 3953 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: 1.3603. Min Range: -1.3603

Max Act: 1.3603. Min Act: -0.0000

Data Index: 291791 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8933. Min Act: -0.0000

Data Index: 143660 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1242589 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1186655 (The Pile)

Max Activating Token Index: 356

Text #4

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8516. Min Act: -0.0000

Data Index: 567966 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1516014 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8326. Min Act: -0.0000

Data Index: 554105 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8953. Min Act: -0.0000

Data Index: 1968127 (The Pile)

Max Activating Token Index: 718

Text #8

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.7608. Min Act: -0.0000

Data Index: 507673 (The Pile)

Max Activating Token Index: 450

Text #9

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8070. Min Act: -0.0000

Data Index: 82083 (The Pile)

Max Activating Token Index: 341

Text #10

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8054. Min Act: -0.0000

Data Index: 160618 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.7644. Min Act: -0.0000

Data Index: 532413 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8337. Min Act: -0.0000

Data Index: 755411 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.7208. Min Act: -0.0000

Data Index: 367059 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.6800. Min Act: -0.0000

Data Index: 694406 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1801538 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.7638. Min Act: -0.0000

Data Index: 517434 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1255177 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1343453 (The Pile)

Max Activating Token Index: 338

Text #19

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1524672 (The Pile)

Max Activating Token Index: 537