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

Dataset: The Pile

Neuron 2165 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.9474. Min Act: -0.0000

Data Index: 1490483 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.3466. Min Act: -0.0000

Data Index: 218447 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.3569. Min Act: -0.0000

Data Index: 640234 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.2125. Min Act: -0.0000

Data Index: 1339221 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.4846. Min Act: -0.0000

Data Index: 1253659 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.0594. Min Act: -0.0000

Data Index: 1329927 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.8814. Min Act: -0.0000

Data Index: 1470148 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.9333. Min Act: -0.0000

Data Index: 961139 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.8748. Min Act: -0.0000

Data Index: 6960 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.8806. Min Act: -0.0000

Data Index: 694791 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.2252. Min Act: -0.0000

Data Index: 1388929 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.0943. Min Act: -0.0000

Data Index: 528048 (The Pile)

Max Activating Token Index: 454

Text #12

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.2504. Min Act: -0.0000

Data Index: 1287625 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.3731. Min Act: -0.0000

Data Index: 1760975 (The Pile)

Max Activating Token Index: 599

Text #14

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1115. Min Act: -0.0000

Data Index: 1900393 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.8537. Min Act: -0.0000

Data Index: 1056232 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.7752. Min Act: -0.0000

Data Index: 1215152 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.8718. Min Act: -0.0000

Data Index: 1112306 (The Pile)

Max Activating Token Index: 116

Text #18

Max Range: 3.3569. Min Range: -3.3569

Max Act: 2.2624. Min Act: -0.0000

Data Index: 1430575 (The Pile)

Max Activating Token Index: 820

Text #19

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1610. Min Act: -0.0000

Data Index: 618975 (The Pile)

Max Activating Token Index: 300