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

Dataset: The Pile

Neuron 3738 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: 1.8981. Min Range: -1.8981

Max Act: 1.8981. Min Act: -0.0000

Data Index: 127317 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.5335. Min Act: -0.0000

Data Index: 1648648 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.6475. Min Act: -0.0000

Data Index: 705977 (The Pile)

Max Activating Token Index: 612

Text #3

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.7809. Min Act: -0.0000

Data Index: 441057 (The Pile)

Max Activating Token Index: 906

Text #4

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.6588. Min Act: -0.0000

Data Index: 1999561 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.6108. Min Act: -0.0000

Data Index: 1894293 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.6701. Min Act: -0.0000

Data Index: 996118 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.6110. Min Act: -0.0000

Data Index: 803992 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4947. Min Act: -0.0000

Data Index: 1433648 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.5218. Min Act: -0.0000

Data Index: 1293810 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4800. Min Act: -0.0000

Data Index: 1251579 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.3482. Min Act: -0.0000

Data Index: 562457 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.3396. Min Act: -0.0000

Data Index: 642123 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4161. Min Act: -0.0000

Data Index: 1243115 (The Pile)

Max Activating Token Index: 830

Text #14

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.3065. Min Act: -0.0000

Data Index: 1119677 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4394. Min Act: -0.0000

Data Index: 1113218 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.2856. Min Act: -0.0000

Data Index: 459509 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4164. Min Act: -0.0000

Data Index: 1658565 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1491348 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.3711. Min Act: -0.0000

Data Index: 968551 (The Pile)

Max Activating Token Index: 87