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

Dataset: The Pile

Neuron 1048 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: 1.4572. Min Range: -1.4572

Max Act: 1.4572. Min Act: -0.0000

Data Index: 1632753 (The Pile)

Max Activating Token Index: 609

Text #1

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.2418. Min Act: -0.0000

Data Index: 1098400 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1048012 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1966519 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.2146. Min Act: -0.0000

Data Index: 1612537 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3518. Min Act: -0.0000

Data Index: 1402355 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3281. Min Act: -0.0000

Data Index: 560566 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1670. Min Act: -0.0000

Data Index: 122319 (The Pile)

Max Activating Token Index: 923

Text #8

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1812852 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3168. Min Act: -0.0000

Data Index: 1792758 (The Pile)

Max Activating Token Index: 715

Text #10

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1124. Min Act: -0.0000

Data Index: 785986 (The Pile)

Max Activating Token Index: 581

Text #11

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1858. Min Act: -0.0000

Data Index: 165677 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1659. Min Act: -0.0000

Data Index: 900020 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1780. Min Act: -0.0000

Data Index: 252137 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1867758 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1602. Min Act: -0.0000

Data Index: 525470 (The Pile)

Max Activating Token Index: 434

Text #16

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1453. Min Act: -0.0000

Data Index: 1139331 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1526. Min Act: -0.0000

Data Index: 693611 (The Pile)

Max Activating Token Index: 594

Text #18

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1472. Min Act: -0.0000

Data Index: 298063 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1691373 (The Pile)

Max Activating Token Index: 853