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

Dataset: The Pile

Neuron 3119 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.5529. Min Act: -0.0000

Data Index: 1552480 (The Pile)

Max Activating Token Index: 375

Text #1

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4959. Min Act: -0.0000

Data Index: 356723 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3269. Min Act: -0.0000

Data Index: 1885713 (The Pile)

Max Activating Token Index: 999

Text #3

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3923. Min Act: -0.0000

Data Index: 1362532 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4472. Min Act: -0.0000

Data Index: 1376219 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3022. Min Act: -0.0000

Data Index: 1694572 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1959332 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2583. Min Act: -0.0000

Data Index: 675997 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2843. Min Act: -0.0000

Data Index: 438883 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2838. Min Act: -0.0000

Data Index: 1078617 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2864. Min Act: -0.0000

Data Index: 79048 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2445. Min Act: -0.0000

Data Index: 1341608 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1920959 (The Pile)

Max Activating Token Index: 678

Text #13

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1306774 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1914. Min Act: -0.0000

Data Index: 1656501 (The Pile)

Max Activating Token Index: 946

Text #15

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0986. Min Act: -0.0000

Data Index: 770084 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0497. Min Act: -0.0000

Data Index: 1997326 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1274. Min Act: -0.0000

Data Index: 734824 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0687. Min Act: -0.0000

Data Index: 1259515 (The Pile)

Max Activating Token Index: 125

Text #19

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1627828 (The Pile)

Max Activating Token Index: 471