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

Dataset: The Pile

Neuron 1453 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: 3.2864. Min Range: -3.2864

Max Act: 3.0625. Min Act: -0.0000

Data Index: 746276 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 3.2864. Min Range: -3.2864

Max Act: 3.2864. Min Act: -0.0000

Data Index: 1516046 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.9884. Min Act: -0.0000

Data Index: 1973073 (The Pile)

Max Activating Token Index: 741

Text #3

Max Range: 3.2864. Min Range: -3.2864

Max Act: 3.0694. Min Act: -0.0000

Data Index: 302499 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.3292. Min Act: -0.0000

Data Index: 1419615 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.6827. Min Act: -0.0000

Data Index: 1504589 (The Pile)

Max Activating Token Index: 730

Text #6

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.6135. Min Act: -0.0000

Data Index: 1087065 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.8357. Min Act: -0.0000

Data Index: 1257219 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.2065. Min Act: -0.0000

Data Index: 1946792 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.3054. Min Act: -0.0000

Data Index: 189863 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.4424. Min Act: -0.0000

Data Index: 1112814 (The Pile)

Max Activating Token Index: 265

Text #11

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.3933. Min Act: -0.0000

Data Index: 757464 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.6158. Min Act: -0.0000

Data Index: 631095 (The Pile)

Max Activating Token Index: 668

Text #13

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.2689. Min Act: -0.0000

Data Index: 175908 (The Pile)

Max Activating Token Index: 192

Text #14

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.2475. Min Act: -0.0000

Data Index: 1319758 (The Pile)

Max Activating Token Index: 736

Text #15

Max Range: 3.2864. Min Range: -3.2864

Max Act: 1.9232. Min Act: -0.0000

Data Index: 917050 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.2137. Min Act: -0.0000

Data Index: 1475014 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.3511. Min Act: -0.0000

Data Index: 56893 (The Pile)

Max Activating Token Index: 496

Text #18

Max Range: 3.2864. Min Range: -3.2864

Max Act: 1.9832. Min Act: -0.0000

Data Index: 1651241 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 3.2864. Min Range: -3.2864

Max Act: 2.0217. Min Act: -0.0000

Data Index: 1130213 (The Pile)

Max Activating Token Index: 805