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

Dataset: The Pile

Neuron 4012 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2617. Min Range: -1.2617

Max Act: 1.2617. Min Act: -0.0000

Data Index: 939215 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 1.2617. Min Range: -1.2617

Max Act: 1.0973. Min Act: -0.0000

Data Index: 1775138 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 1.2617. Min Range: -1.2617

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1837476 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 1.2617. Min Range: -1.2617

Max Act: 1.0956. Min Act: -0.0000

Data Index: 326545 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 1.2617. Min Range: -1.2617

Max Act: 1.1855. Min Act: -0.0000

Data Index: 1683221 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 1.2617. Min Range: -1.2617

Max Act: 1.0881. Min Act: -0.0000

Data Index: 895647 (The Pile)

Max Activating Token Index: 908

Text #6

Max Range: 1.2617. Min Range: -1.2617

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1501152 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 1.2617. Min Range: -1.2617

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1689798 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 1.2617. Min Range: -1.2617

Max Act: 0.9866. Min Act: -0.0000

Data Index: 49291 (The Pile)

Max Activating Token Index: 889

Text #9

Max Range: 1.2617. Min Range: -1.2617

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1659490 (The Pile)

Max Activating Token Index: 161

Text #10

Max Range: 1.2617. Min Range: -1.2617

Max Act: 1.0921. Min Act: -0.0000

Data Index: 1144373 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 1.2617. Min Range: -1.2617

Max Act: 0.9776. Min Act: 0.0000

Data Index: 1183787 (The Pile)

Max Activating Token Index: 117

Text #12

Max Range: 1.2617. Min Range: -1.2617

Max Act: 0.9959. Min Act: -0.0000

Data Index: 1182773 (The Pile)

Max Activating Token Index: 237

Text #13

Max Range: 1.2617. Min Range: -1.2617

Max Act: 0.9991. Min Act: -0.0000

Data Index: 708814 (The Pile)

Max Activating Token Index: 428

Text #14

Max Range: 1.2617. Min Range: -1.2617

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1633967 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 1.2617. Min Range: -1.2617

Max Act: 0.9586. Min Act: -0.0000

Data Index: 182195 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 1.2617. Min Range: -1.2617

Max Act: 0.7977. Min Act: -0.0000

Data Index: 641826 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 1.2617. Min Range: -1.2617

Max Act: 0.7940. Min Act: -0.0000

Data Index: 881992 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 1.2617. Min Range: -1.2617

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1494959 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 1.2617. Min Range: -1.2617

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1287263 (The Pile)

Max Activating Token Index: 991