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

Dataset: The Pile

Neuron 55 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1862600 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.2054. Min Act: -0.0000

Data Index: 231095 (The Pile)

Max Activating Token Index: 545

Text #2

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1951. Min Act: -0.0000

Data Index: 555481 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1902. Min Act: -0.0000

Data Index: 600810 (The Pile)

Max Activating Token Index: 201

Text #4

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1787. Min Act: -0.0000

Data Index: 994648 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1605. Min Act: -0.0000

Data Index: 214733 (The Pile)

Max Activating Token Index: 971

Text #6

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1706. Min Act: -0.0000

Data Index: 139818 (The Pile)

Max Activating Token Index: 373

Text #7

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1370100 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1409741 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1500. Min Act: -0.0000

Data Index: 75789 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1002742 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1574. Min Act: -0.0000

Data Index: 694773 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1654764 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1379010 (The Pile)

Max Activating Token Index: 301

Text #14

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1586. Min Act: -0.0000

Data Index: 466974 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1120838 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1566. Min Act: -0.0000

Data Index: 735604 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1392. Min Act: -0.0000

Data Index: 670869 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1003652 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1347630 (The Pile)

Max Activating Token Index: 1022