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

Dataset: The Pile

Neuron 3476 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: 0.2589. Min Range: -0.2589

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1138772 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2245. Min Act: -0.0000

Data Index: 41859 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1635215 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1429344 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1720. Min Act: -0.0000

Data Index: 563655 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1902. Min Act: -0.0000

Data Index: 585640 (The Pile)

Max Activating Token Index: 590

Text #6

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1748. Min Act: -0.0000

Data Index: 565774 (The Pile)

Max Activating Token Index: 51

Text #7

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1710843 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1306881 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1719. Min Act: -0.0000

Data Index: 639184 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1648. Min Act: -0.0000

Data Index: 959670 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1701. Min Act: -0.0000

Data Index: 178249 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1006246 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1155848 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1166377 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1660. Min Act: -0.0000

Data Index: 672775 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1242487 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1134567 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1428. Min Act: -0.0000

Data Index: 870952 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1961875 (The Pile)

Max Activating Token Index: 808